© 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. 50912
    Prev
    Next
    INDEX
    Explanations

    poetry

    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
    Ŀ
    -0.07
     entitlement
    -0.07
    ㎧
    -0.07
     pantry
    -0.07
     שאינו
    -0.06
    QUI
    -0.06
     outnumber
    -0.06
    ustainability
    -0.06
    daughter
    -0.06
    废话
    -0.06
    POSITIVE LOGITS
    (doc
    0.07
     regularization
    0.07
     ")"
    0.06
     Rew
    0.06
    GetMethod
    0.06
     Sig
    0.06
     Rob
    0.06
     Kom
    0.06
     Axel
    0.06
     electrode
    0.06
    Activations Density 0.008%

    No Known Activations