© 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. 129597
    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
    izard
    -0.27
    ovsky
    -0.25
    æĹłè®ºå¦Ĥä½ķ
    -0.25
     fewer
    -0.24
    enty
    -0.24
     СеÑĢ
    -0.24
    éĵł
    -0.24
    ^-
    -0.23
    afd
    -0.23
    imas
    -0.23
    POSITIVE LOGITS
    çı¥
    0.25
    _Channel
    0.23
    emi
    0.23
     dens
    0.23
    eks
    0.23
    ilians
    0.23
    exus
    0.23
    )test
    0.23
    è®°
    0.23
    rellas
    0.22
    Activations Density 25.233%

    No Known Activations

    This feature has no known activations.