© 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. 12-TRANSCODER-HP
    7. 23136
    Prev
    Next
    INDEX
    Explanations

    Swearing/vulgar slang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rito
    -0.30
     cop
    -0.29
    cop
    -0.28
    Cop
    -0.28
    culo
    -0.27
    _Pos
    -0.27
    _UNITS
    -0.27
    ppy
    -0.26
    åĸĦ
    -0.25
     cân
    -0.25
    POSITIVE LOGITS
    ((_
    0.30
     figuring
    0.30
    为äºĨ让
    0.29
    yahoo
    0.26
    禽
    0.26
    èĽ¾
    0.25
    ä¸Ģæīĭ
    0.25
     nghĩ
    0.25
    -outs
    0.25
    赶ä¸Ĭ
    0.25
    Activations Density 0.014%

    No Known Activations