© 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. 9215
    Prev
    Next
    INDEX
    Explanations

    Measurements and statistics

    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
    ulum
    -0.28
    osos
    -0.28
     Sob
    -0.26
    æŃ¢
    -0.26
     [[[
    -0.25
    antage
    -0.24
    imony
    -0.24
    ä¾
    -0.24
    perse
    -0.24
    uni
    -0.24
    POSITIVE LOGITS
     trail
    0.28
     Trail
    0.26
     darkest
    0.26
    è°¿
    0.26
    强åĮĸ
    0.26
     crush
    0.25
     nearest
    0.25
    aeda
    0.24
    åİĭå®ŀ
    0.24
     Thinking
    0.24
    Activations Density 0.028%

    No Known Activations