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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64111
    Prev
    Next
    INDEX
    Explanations

    temperature, methods, person's name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trav
    -0.27
    çļĦåIJĮåѦ
    -0.25
    !!)↵
    -0.25
    å±Ĥåĩº
    -0.24
    åģļå®Į
    -0.24
    activities
    -0.24
    AppName
    -0.24
    sville
    -0.24
    azine
    -0.23
    afil
    -0.23
    POSITIVE LOGITS
    çĽ¼
    0.27
     basal
    0.27
    ç«ĭåľº
    0.27
    èĹ¿
    0.26
     Å
    0.26
    æĻ¯
    0.26
    èŀºæĹĭ
    0.24
    éĺ²çģ«
    0.24
    ix
    0.24
    æł¼å±Ģ
    0.24
    Activations Density 12.434%

    No Known Activations