© 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. 19-TRANSCODER-HP
    7. 7972
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à´´
    -0.29
    EMPTY
    -0.29
    zers
    -0.28
    oldown
    -0.28
    æłĸ
    -0.28
    мож
    -0.27
     Teachers
    -0.26
    icaid
    -0.26
     Balt
    -0.25
    åĿ»
    -0.25
    POSITIVE LOGITS
    finger
    0.26
    ÅŁa
    0.26
    ä¸Ŀ毫
    0.26
     unique
    0.25
    sw
    0.25
     bes
    0.25
    è¹¼
    0.25
    iful
    0.24
    åı£æ°´
    0.24
     Synopsis
    0.23
    Activations Density 0.029%

    No Known Activations