© 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. 129432
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
     money
    -0.27
     ancient
    -0.25
    aky
    -0.25
    ãĤīãģı
    -0.25
    éĴ±
    -0.25
     B
    -0.25
    affer
    -0.25
     old
    -0.25
    L
    -0.25
    lo
    -0.25
    POSITIVE LOGITS
    ç¿ķ
    0.30
    uve
    0.28
    å¤ĩ
    0.27
    /cop
    0.27
    èĺ¸
    0.27
    .ix
    0.26
     seiz
    0.25
    çŃīéĥ¨éŨ
    0.24
    .replaceAll
    0.24
     insure
    0.23
    Activations Density 8.058%

    No Known Activations