© 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. 141584
    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
    (zip
    -0.29
    ä¹Łåıªæľī
    -0.26
    æĦĶ
    -0.26
    éĥ¨åī¯éĥ¨éķ¿
    -0.26
    éľĨ
    -0.26
    aab
    -0.25
    dge
    -0.24
    ä¹°åĪ°
    -0.24
    ä»ħæľī
    -0.24
     touched
    -0.24
    POSITIVE LOGITS
    rador
    0.32
    å±¥
    0.26
    ør
    0.26
    Clo
    0.26
    æĤŁ
    0.26
    /pi
    0.26
    orsk
    0.25
     morals
    0.25
     Curry
    0.25
     pi
    0.24
    Activations Density 7.337%

    No Known Activations

    This feature has no known activations.