© 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. 15-RESID-POST-AA
    11. 18616
    Prev
    Next
    INDEX
    Explanations

    strategy

    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
    Negative Logits
    葳
    -0.08
     salle
    -0.08
    堆放
    -0.07
    produto
    -0.07
    価
    -0.07
    <Vec
    -0.07
    委托
    -0.07
     (((
    -0.07
    atrice
    -0.06
     sư
    -0.06
    POSITIVE LOGITS
    -active
    0.08
    되지
    0.07
    ciąg
    0.07
    뉘
    0.07
     다르
    0.07
     October
    0.07
    说得
    0.07
     okre
    0.07
    한
    0.07
    に行った
    0.07
    Activations Density 0.109%

    No Known Activations