© 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. 129716
    Prev
    Next
    INDEX
    Explanations

    me

    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
     Whale
    -0.26
    éĻ¤æѤ
    -0.26
    mina
    -0.26
    [prop
    -0.24
    jack
    -0.24
    ,Q
    -0.24
    èĤª
    -0.24
    ãĢģãĢĮ
    -0.24
    Nine
    -0.23
     fruitful
    -0.23
    POSITIVE LOGITS
    /
    0.27
     uncomp
    0.26
    /o
    0.26
    éĵ¢
    0.26
    achinery
    0.26
    usto
    0.25
     Hutchinson
    0.25
    -č↵
    0.25
    ç»Ļ
    0.24
    -or
    0.24
    Activations Density 73.722%

    No Known Activations