© 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. 18-TRANSCODER-HP
    7. 88768
    Prev
    Next
    INDEX
    Explanations

    Code, documentation, or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĶåĽŀæIJľçĭIJ
    -0.26
    ä¸ºæł¸å¿ĥçļĦ
    -0.25
     impair
    -0.25
    -ignore
    -0.25
     buffet
    -0.24
    æ°Ķè´¨
    -0.24
    ="[
    -0.23
     Vol
    -0.23
    lose
    -0.23
     ignoring
    -0.23
    POSITIVE LOGITS
    ately
    0.31
    [âĢ¦
    0.28
    edin
    0.26
    inine
    0.25
    ’est
    0.25
    年以æĿ¥
    0.24
     FuÃŁ
    0.24
    yleft
    0.24
    产
    0.24
     trous
    0.24
    Activations Density 1.530%

    No Known Activations