© 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. 142019
    Prev
    Next
    INDEX
    Explanations

    Mathematical problems/proofs

    np_max-act · gemini-2.0-flash
    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
    elo
    -0.29
    PageIndex
    -0.27
    bre
    -0.26
     ÑģкаÑĩ
    -0.26
    èĥ¸éĥ¨
    -0.24
     kal
    -0.24
    Coefficient
    -0.24
     borrowed
    -0.24
    åģ·
    -0.24
     dr
    -0.24
    POSITIVE LOGITS
     every
    0.42
     EVERY
    0.38
    åĩłä¹İæīĢæľī
    0.37
     everywhere
    0.37
     everyone
    0.36
    æīĢæľī人éĥ½
    0.35
    every
    0.35
    æīĢæľī
    0.34
    everyone
    0.34
    Every
    0.33
    Activations Density 8.741%

    No Known Activations