© 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. 63798
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    á¿ĸ
    -0.29
     panels
    -0.28
    åĻ¨
    -0.26
    ur
    -0.26
    Äħż
    -0.26
    ikit
    -0.25
     ur
    -0.25
    _panel
    -0.25
    uraa
    -0.25
    urable
    -0.25
    POSITIVE LOGITS
    oni
    0.31
    eman
    0.29
    _hard
    0.28
     Fellowship
    0.27
    hp
    0.25
    QP
    0.25
    enco
    0.25
     ÐĴо
    0.25
    prot
    0.25
    gent
    0.24
    Activations Density 4.123%

    No Known Activations

    This feature has no known activations.