© 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 EvalsExportsAPI 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. 69595
    Prev
    Next
    INDEX
    Explanations

    stock photo disclaimer

    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
    rende
    -0.08
     Coil
    -0.08
     Yah
    -0.08
     khoản
    -0.07
    Tok
    -0.07
     yuk
    -0.07
    ăm
    -0.07
    沘
    -0.07
     espaço
    -0.06
     komt
    -0.06
    POSITIVE LOGITS
    طبع
    0.07
    著
    0.07
    ╗
    0.07
    首选
    0.07
     genu
    0.07
    _results
    0.07
    pageIndex
    0.07
    neutral
    0.07
     ------>
    0.06
     appreh
    0.06
    Activations Density 0.008%

    No Known Activations