© 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. 89366
    Prev
    Next
    INDEX
    Explanations

    texts

    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
    lim
    -0.27
    datasets
    -0.26
    ç¨ĭåºı
    -0.26
    -console
    -0.25
    è¿IJæ°Ķ
    -0.24
    illi
    -0.24
    çŨ
    -0.24
    åIJ¬åIJ¬
    -0.24
     Dataset
    -0.24
     Bir
    -0.24
    POSITIVE LOGITS
    éĨĽ
    0.29
    éĨ
    0.29
    è°ģçŁ¥éģĵ
    0.27
    ullen
    0.26
    FunctionFlags
    0.26
    åľ°æĸ¹
    0.25
    .columns
    0.25
    ä¸į认è¯Ĩ
    0.25
    åĿIJçĿĢ
    0.24
    èĴ¡
    0.24
    Activations Density 12.831%

    No Known Activations