© 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. 31321
    Prev
    Next
    INDEX
    Explanations

    check

    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
    燧
    -0.08
     Ngb
    -0.08
    善意
    -0.07
     PG
    -0.07
    钿
    -0.07
    梣
    -0.07
    שפ
    -0.07
    �
    -0.07
    薪
    -0.07
    <D
    -0.07
    POSITIVE LOGITS
     Kami
    0.08
     לראות
    0.08
    并通过
    0.07
    меча
    0.07
    できて
    0.07
    emin
    0.07
     Robbins
    0.06
    nil
    0.06
    imen
    0.06
    第三届
    0.06
    Activations Density 0.015%

    No Known Activations