© 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. 11-RESID-POST-AA
    11. 72162
    Prev
    Next
    INDEX
    Explanations

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     norske
    -0.07
    핮
    -0.06
    创新发展
    -0.06
    .Cache
    -0.06
    _cores
    -0.06
    ILLE
    -0.06
     todav
    -0.06
    ifiable
    -0.06
     IX
    -0.06
     kaç
    -0.06
    POSITIVE LOGITS
    _theme
    0.07
     bonus
    0.07
     behaviours
    0.07
    植物
    0.07
    _options
    0.07
    imp
    0.07
     Preference
    0.07
     booster
    0.07
    onyms
    0.07
     ambient
    0.07
    Activations Density 0.002%

    No Known Activations