© 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. 23360
    Prev
    Next
    INDEX
    Explanations

    Lower body parts

    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
    ä¸įè§ģ
    -0.28
     bell
    -0.27
    otted
    -0.27
    ä¹ī
    -0.27
    渥
    -0.26
    ä¸Ģ对
    -0.25
    çĭ±
    -0.25
    å¯Ŀ
    -0.25
    æµĥ
    -0.24
     equipo
    -0.24
    POSITIVE LOGITS
    INY
    0.29
    -anchor
    0.28
    å¾Ģå¹´
    0.25
    åħ¥å¢ĥ
    0.25
    avo
    0.25
    -large
    0.25
    .GetCurrent
    0.24
    INSTALL
    0.24
    ypad
    0.24
    ä»İåݻ年
    0.24
    Activations Density 0.004%

    No Known Activations