© 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. 62979
    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
     assist
    -0.27
    nj
    -0.27
    nr
    -0.27
     sno
    -0.25
    vr
    -0.25
     aj
    -0.25
     Pref
    -0.25
     Ass
    -0.24
    ä»°
    -0.24
    -tags
    -0.24
    POSITIVE LOGITS
    ibble
    0.29
    åıªèĥ½è¯´
    0.29
    odes
    0.28
    iets
    0.27
    æ¦Ĩ
    0.26
    تÙģاصÙĬÙĦ
    0.25
    enuous
    0.24
    æĸ°æĹ¶æľŁ
    0.24
    BAB
    0.24
    İĺìĿ´
    0.24
    Activations Density 30.759%

    No Known Activations

    This feature has no known activations.