© 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. 80400
    Prev
    Next
    INDEX
    Explanations

    liability

    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
    /module
    -0.07
    献血
    -0.07
     hạt
    -0.07
    x
    -0.07
     passports
    -0.07
     important
    -0.07
     PropertyValue
    -0.07
    ┿
    -0.06
     importantes
    -0.06
    ultipartFile
    -0.06
    POSITIVE LOGITS
    Does
    0.08
    (Expected
    0.07
    具体内容
    0.07
    得很好
    0.07
    严格的
    0.07
    个人观点
    0.07
     conclude
    0.07
    教你
    0.07
     lowered
    0.07
    .rl
    0.07
    Activations Density 0.004%

    No Known Activations