© 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. 19-RESID-POST-AA
    11. 54353
    Prev
    Next
    INDEX
    Explanations

    but

    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
    Negative Logits
     auss
    -0.07
     plumber
    -0.07
     showAlert
    -0.07
    𝘙
    -0.07
    🕗
    -0.07
    .reducer
    -0.07
    อำ
    -0.07
     staffer
    -0.07
     עדיין
    -0.07
     alguna
    -0.07
    POSITIVE LOGITS
     mainAxisAlignment
    0.07
    גם
    0.07
    读后感
    0.07
    مكونات
    0.07
     геро
    0.06
    𝘭
    0.06
     Dear
    0.06
    خاص
    0.06
    Because
    0.06
    near
    0.06
    Activations Density 0.075%

    No Known Activations