© 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. 4863
    Prev
    Next
    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash
    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
    .*)
    -0.07
     Suc
    -0.07
    숯
    -0.07
     gov
    -0.07
    丝毫不
    -0.07
     июля
    -0.07
    arus
    -0.06
    괌
    -0.06
    匍
    -0.06
     mundo
    -0.06
    POSITIVE LOGITS
    robe
    0.08
    translation
    0.08
    letter
    0.08
    (idx
    0.07
     splitter
    0.07
    "name
    0.07
    ibBundleOrNil
    0.07
    剩下
    0.07
    (found
    0.07
    ignal
    0.07
    Activations Density 0.021%

    No Known Activations