© 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. 141243
    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
     Maher
    -0.28
    æ±²åıĸ
    -0.26
    åIJ¸æĶ¶
    -0.26
     appropriations
    -0.24
    tail
    -0.24
     INCLUDED
    -0.24
    aux
    -0.23
    Concept
    -0.23
     напÑĢавлен
    -0.23
    unity
    -0.23
    POSITIVE LOGITS
    arse
    0.28
    held
    0.28
    .getView
    0.25
     getClient
    0.24
     Gun
    0.24
    å½ĵåľ°æŶéĹ´
    0.24
     histories
    0.24
     geopol
    0.23
    åıĹ害
    0.23
    -gun
    0.23
    Activations Density 14.604%

    No Known Activations

    This feature has no known activations.