© 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. 113805
    Prev
    Next
    INDEX
    Explanations

    Russian words

    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
     invert
    -0.08
    nosis
    -0.07
    Ｚ
    -0.07
    MERCHANTABILITY
    -0.07
    цикл
    -0.07
    .splitext
    -0.07
    投資
    -0.07
    热心
    -0.07
    	of
    -0.07
    NOT
    -0.07
    POSITIVE LOGITS
    寨
    0.07
    篥
    0.07
    라고
    0.07
     ear
    0.07
    igan
    0.07
    .fast
    0.06
    illet
    0.06
    (rb
    0.06
    edo
    0.06
    -record
    0.06
    Activations Density 0.017%

    No Known Activations