© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 73093
    Prev
    Next
    INDEX
    Explanations

    sentences or tokens that give explicit instructions about the assistant's role/behavior (roleplay/system directives and similar meta-instructions).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zro
    -0.07
     Alle
    -0.07
     +#+
    -0.07
    xce
    -0.06
    Ꙭ
    -0.06
    ellaneous
    -0.06
     Nich
    -0.06
    getattr
    -0.06
     Azerbai
    -0.06
     hatch
    -0.06
    POSITIVE LOGITS
    预售
    0.07
    הקמת
    0.07
    LOSS
    0.07
     TString
    0.06
    ሽ
    0.06
    萝卜
    0.06
    alpha
    0.06
    -auth
    0.06
     breakpoints
    0.06
    unities
    0.06
    Activations Density 0.140%

    No Known Activations