© 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. 107664
    Prev
    Next
    INDEX
    Explanations

    Software and configuration

    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
     hawk
    -0.28
    éĢĴ
    -0.27
     Kay
    -0.27
    åħ¨æµģç¨ĭ
    -0.26
    è´´
    -0.26
    ORY
    -0.25
    ãĤĤãģ®
    -0.25
    好ä¸į好
    -0.25
    Kay
    -0.25
     Hawks
    -0.24
    POSITIVE LOGITS
    ificant
    0.30
    nings
    0.27
    ReturnValue
    0.26
    _FALSE
    0.25
    venta
    0.24
    chema
    0.24
    -describedby
    0.23
    aData
    0.23
    ledged
    0.23
    ->[
    0.23
    Activations Density 32.851%

    No Known Activations