© 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. 107886
    Prev
    Next
    INDEX
    Explanations

    Press associations

    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
    åīįåĪĹ
    -0.28
    issan
    -0.28
    çļĦåĬŀæ³ķ
    -0.25
    ä¸ĢæĬĬ
    -0.25
    çļĦæľºä¼ļ
    -0.25
    lad
    -0.25
     Turner
    -0.25
    第ä¸Ģ天
    -0.24
    ģ
    -0.24
    locator
    -0.24
    POSITIVE LOGITS
    æ¼Ķç»İ
    0.28
    gross
    0.26
     gross
    0.26
    educt
    0.26
    ded
    0.26
    èĴ¯
    0.25
    ä¼ł
    0.25
    cff
    0.25
    è¯Ńè¨Ģ
    0.25
    дон
    0.25
    Activations Density 1.006%

    No Known Activations