© 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. 72126
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Global
    -0.07
    融合
    -0.07
    aycast
    -0.06
    ím
    -0.06
    pecial
    -0.06
    ודי
    -0.06
    كسر
    -0.06
    avier
    -0.06
     chatter
    -0.06
    arma
    -0.06
    POSITIVE LOGITS
    "><?
    0.07
    瀏
    0.07
     knitting
    0.07
     martin
    0.06
    🏋
    0.06
    TestMethod
    0.06
    รายงาน
    0.06
    ':{'
    0.06
     Smarty
    0.06
     ואח
    0.06
    Activations Density 0.027%

    No Known Activations