© 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. 63682
    Prev
    Next
    INDEX
    Explanations

    day

    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
    udu
    -0.30
    _controls
    -0.27
     (("
    -0.27
    æİ¢
    -0.26
    omo
    -0.26
     Predictor
    -0.25
     weekends
    -0.25
    abox
    -0.25
    åģĩæĹ¥
    -0.25
    æİīäºĨ
    -0.25
    POSITIVE LOGITS
    åIJĪæ³ķæĢ§
    0.31
    ilarity
    0.26
    eenth
    0.26
    enance
    0.25
    -good
    0.25
    ç½Ħ
    0.25
     disin
    0.24
    产ä¸ļåĽŃåĮº
    0.24
    ä¼ļ使
    0.24
    æ²Ĩ
    0.23
    Activations Density 8.202%

    No Known Activations