© 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. 20-TRANSCODER-HP
    7. 63013
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emer
    -0.25
    åĵģç§į
    -0.25
    oods
    -0.24
    ä¸ĩåIJį
    -0.24
     destino
    -0.23
    ä¸ĢçĤ¹çĤ¹
    -0.23
     interrupts
    -0.23
    _SO
    -0.23
    Louis
    -0.23
    æļ´
    -0.23
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.47
    æľ¬èº«
    0.40
    ä»ĸèĩªå·±
    0.34
    æľ¬èº«å°±æĺ¯
    0.33
     themselves
    0.30
     actual
    0.30
     himself
    0.29
     itself
    0.29
    æľ¬èº«å°±
    0.29
    佩æľį
    0.29
    Activations Density 59.567%

    No Known Activations