© 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. 45704
    Prev
    Next
    INDEX
    Explanations

    who

    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
     Almost
    -0.07
    appen
    -0.07
    lesen
    -0.07
    ому
    -0.07
    全域旅游
    -0.07
     Reception
    -0.07
    they
    -0.07
    痓
    -0.07
    อบรม
    -0.07
    öl
    -0.07
    POSITIVE LOGITS
     dan
    0.07
    玩家
    0.07
    ="$(
    0.07
    	namespace
    0.07
    ('
    0.06
    ?('
    0.06
    였다
    0.06
     engines
    0.06
     cler
    0.06
    没有必要
    0.06
    Activations Density 0.055%

    No Known Activations