© 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. 9121
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    æī¿
    -0.26
    åĪĿæģĭ
    -0.25
     ($)
    -0.25
    pany
    -0.24
    hone
    -0.24
     junior
    -0.24
     Cunningham
    -0.24
     Hampton
    -0.24
    Charset
    -0.23
     Daly
    -0.23
    POSITIVE LOGITS
    èĩªå·±åĸľæ¬¢
    0.31
    ergy
    0.29
     itself
    0.28
    æĪĸå¤ļ
    0.28
    ande
    0.27
    æľ¬èº«
    0.26
    åIJij举
    0.25
    åıĬ缸åħ³
    0.25
    andon
    0.24
    ÑĨа
    0.24
    Activations Density 0.001%

    No Known Activations