© 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. 5517
    Prev
    Next
    INDEX
    Explanations

    Calls to action

    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
    _CLIP
    -0.08
    mailbox
    -0.07
     Cincinnati
    -0.07
    Vision
    -0.07
    Bus
    -0.07
     مليون
    -0.07
     scripted
    -0.07
    фин
    -0.07
    sprintf
    -0.07
     toujours
    -0.06
    POSITIVE LOGITS
    .GroupLayout
    0.08
    IN
    0.07
    少吃
    0.07
    -transitional
    0.06
    ises
    0.06
    쌓
    0.06
    uspendLayout
    0.06
    т
    0.06
    뎁
    0.06
     springs
    0.06
    Activations Density 0.106%

    No Known Activations