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

    Neuronpedia

    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. 5002
    Prev
    Next
    INDEX
    Explanations

    Animal-assisted therapy

    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
    国籍
    -0.07
    вести
    -0.07
     Saint
    -0.07
     tới
    -0.07
    _draw
    -0.07
    ⌒
    -0.06
    _Clear
    -0.06
    Previous
    -0.06
    𝕜
    -0.06
    🐨
    -0.06
    POSITIVE LOGITS
    isodes
    0.07
     troubles
    0.07
    genesis
    0.07
    ➸
    0.06
    ens
    0.06
    umen
    0.06
    その他
    0.06
    พฤศจ
    0.06
    ucing
    0.06
     mạnh
    0.06
    Activations Density 0.034%

    No Known Activations