© 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. 64119
    Prev
    Next
    INDEX
    Explanations

    Preventing future events

    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
     cul
    -0.30
    proxy
    -0.28
    åĽŀéģ¿
    -0.27
    æıĨ
    -0.26
    kont
    -0.25
    åįĬ
    -0.25
    isque
    -0.25
    -proxy
    -0.25
     paj
    -0.25
    quarters
    -0.24
    POSITIVE LOGITS
    åı¯èĥ½åŃĺåľ¨
    0.28
     wedge
    0.27
     Underground
    0.25
     cyclic
    0.25
     proverb
    0.24
    \Lib
    0.24
    mate
    0.24
     rode
    0.24
     Article
    0.23
    tring
    0.23
    Activations Density 14.934%

    No Known Activations