© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28376
    Prev
    Next
    INDEX
    Explanations

    violence and monsters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     freeze
    -0.07
    <<
    -0.07
    商报
    -0.07
    -Q
    -0.07
    辛
    -0.06
    .junit
    -0.06
    _git
    -0.06
     Repository
    -0.06
    late
    -0.06
    仲
    -0.06
    POSITIVE LOGITS
     weap
    0.08
    𬘓
    0.08
    武侠
    0.07
     mundo
    0.07
     Wireless
    0.07
     Alone
    0.07
     Đến
    0.07
    游戏角色
    0.06
     MMO
    0.06
    /engine
    0.06
    Activations Density 0.110%

    No Known Activations