© 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. 7-RESID-POST-AA
    11. 81642
    Prev
    Next
    INDEX
    Explanations

    connector

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peril
    -0.08
     encoded
    -0.07
    riba
    -0.07
     valor
    -0.07
    ursor
    -0.07
    情景
    -0.07
    歧
    -0.07
    jin
    -0.06
    火烧
    -0.06
    Providers
    -0.06
    POSITIVE LOGITS
    ê
    0.09
     Sund
    0.08
    .getBoolean
    0.07
     Playlist
    0.07
     conglomer
    0.07
    ETA
    0.07
    Ṧ
    0.06
    ҽ
    0.06
     cdecl
    0.06
     outlets
    0.06
    Activations Density 0.079%

    No Known Activations