© 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. 11-RESID-POST-AA
    11. 71314
    Prev
    Next
    INDEX
    Explanations

    a

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﰃ
    -0.07
    .matcher
    -0.06
     speakers
    -0.06
    馅
    -0.06
    規
    -0.06
    _patterns
    -0.06
    (Const
    -0.06
    쑹
    -0.06
     distancing
    -0.06
    she
    -0.06
    POSITIVE LOGITS
     élevé
    0.08
     ℕ
    0.08
    IVE
    0.07
    ﻕ
    0.07
     материалы
    0.07
    سين
    0.07
    골
    0.07
     noche
    0.07
    㧟
    0.07
    =event
    0.07
    Activations Density 0.074%

    No Known Activations