© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 113036
    Prev
    Next
    INDEX
    Explanations

    ves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    phans
    -0.26
    éĤ£ç§į
    -0.25
    é±
    -0.24
     DataType
    -0.24
    agine
    -0.23
     oper
    -0.23
    ówki
    -0.23
     долго
    -0.23
    дин
    -0.23
    plets
    -0.23
    POSITIVE LOGITS
     accompanying
    0.44
    éħįå¥Ĺ
    0.39
    éĻĦå±ŀ
    0.39
    éĻĦåĬł
    0.35
    ä¼´éļı
    0.35
    éļıåIJİ
    0.34
     subsequent
    0.34
    çĽ¸ä¼´
    0.34
     adjacent
    0.34
     nearby
    0.33
    Activations Density 0.001%

    No Known Activations