© 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. 89721
    Prev
    Next
    INDEX
    Explanations

    special

    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
    pecting
    -0.28
    idders
    -0.27
    ersh
    -0.26
    Fans
    -0.25
    (ver
    -0.25
    ANNER
    -0.25
    erset
    -0.24
    ingles
    -0.24
    ulary
    -0.24
    arnation
    -0.24
    POSITIVE LOGITS
    æĢ»å±Ģ
    0.28
     special
    0.27
     Special
    0.26
    ä¸ĵéĹ¨ä¸º
    0.25
     con
    0.24
    ä¸Ģäºĭ
    0.24
    ``↵
    0.24
    aceous
    0.24
    {*
    0.24
    ije
    0.24
    Activations Density 2.174%

    No Known Activations