© 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. 19-RESID-POST-AA
    11. 70689
    Prev
    Next
    INDEX
    Explanations

    -type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    顺势
    -0.09
    apGestureRecognizer
    -0.07
     massaggi
    -0.07
    缞
    -0.07
    桫
    -0.07
    etheless
    -0.07
    🅴
    -0.07
     thr
    -0.07
     Wax
    -0.07
    ☤
    -0.07
    POSITIVE LOGITS
    렸
    0.08
    랐
    0.07
    儲
    0.07
    .nc
    0.07
     française
    0.07
     humour
    0.06
     Indian
    0.06
    _WEEK
    0.06
    erais
    0.06
     prevented
    0.06
    Activations Density 0.000%

    No Known Activations