© 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. 9179
    Prev
    Next
    INDEX
    Explanations

    start

    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
    Fe
    -0.27
    ä¸įè§ģ
    -0.27
     Fe
    -0.27
    _JO
    -0.24
    Fin
    -0.24
     stor
    -0.23
     Fin
    -0.23
    åħ¬å®īå±Ģ
    -0.23
    аж
    -0.23
    __č↵
    -0.23
    POSITIVE LOGITS
    efully
    0.28
    icode
    0.27
     Tyson
    0.27
    ptype
    0.27
     raised
    0.26
    colo
    0.26
    å¡Į
    0.25
     regularly
    0.24
    lev
    0.24
     offseason
    0.24
    Activations Density 0.253%

    No Known Activations