© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 83371
    Prev
    Next
    INDEX
    Explanations

    Sem

    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
    Negative Logits
     cray
    -0.07
     CHRIST
    -0.07
    Stripe
    -0.07
    Donate
    -0.07
    .onCreate
    -0.07
    =log
    -0.06
     conect
    -0.06
    ONGO
    -0.06
     Purch
    -0.06
    _CONNECT
    -0.06
    POSITIVE LOGITS
    .finished
    0.07
    testimonial
    0.07
    conds
    0.07
    缱
    0.07
    SupportedException
    0.07
    iosk
    0.07
    ynı
    0.07
     lemma
    0.07
     verschiedenen
    0.07
    自分が
    0.07
    Activations Density 0.025%

    No Known Activations