© 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. 142099
    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
    abile
    -0.29
    mania
    -0.26
    è§Ħ
    -0.26
    emet
    -0.26
    tery
    -0.26
    ogi
    -0.26
    emy
    -0.25
     SQLAlchemy
    -0.25
    Priority
    -0.25
     resent
    -0.25
    POSITIVE LOGITS
     Walls
    0.27
     divisible
    0.25
     pessim
    0.25
    åħļé£İå»īæĶ¿
    0.25
    stück
    0.24
    æ·ĭ
    0.24
    ç°¡
    0.24
    jas
    0.24
     vfs
    0.24
    åħļçļĦ建设
    0.23
    Activations Density 2.004%

    No Known Activations

    This feature has no known activations.