© 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. 63240
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    -quarter
    -0.25
     quo
    -0.25
    uplic
    -0.24
    éĹ´çļĦ
    -0.24
    hands
    -0.23
    irk
    -0.23
    uty
    -0.23
    ä»ĸ认为
    -0.23
     bel
    -0.23
    éĸĵãģ«
    -0.23
    POSITIVE LOGITS
    aggi
    0.26
    Turkey
    0.24
    mith
    0.24
    èĨ³é£Ł
    0.24
    زر
    0.24
    ÑĦик
    0.23
    zÄħ
    0.23
    Ùģت
    0.23
    \Backend
    0.23
    èĭķ
    0.23
    Activations Density 25.514%

    No Known Activations