© 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. 129579
    Prev
    Next
    INDEX
    Explanations

    Negative or harmful effects

    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
    ohl
    -0.26
    _books
    -0.26
    ä¼ł
    -0.24
    hoe
    -0.24
    ĥģ
    -0.24
    hits
    -0.23
    ortal
    -0.23
    _atom
    -0.23
    hog
    -0.23
    åħ±è¯Ĩ
    -0.23
    POSITIVE LOGITS
    mbH
    0.26
    çĽijçĿ£æ£ĢæŁ¥
    0.26
    .Stage
    0.26
    åĴĮåħ¶ä»ĸ
    0.26
    appen
    0.26
    UD
    0.26
     suppose
    0.25
    tright
    0.25
    (final
    0.24
    è¯Ńæ³ķ
    0.24
    Activations Density 25.042%

    No Known Activations