© 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
    2. Qwen3-4B
    3. 20-TRANSCODER-HP
    4. 63369
    Prev
    Next
    INDEX
    Explanations

    technical/factual texts

    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
    æĮĪ
    -0.30
    读åIJİ
    -0.27
    æĮ¯
    -0.27
    å¼ĢçĿĢ
    -0.27
    rand
    -0.27
    ä¸įè¿ľ
    -0.26
    è¦ģ好好
    -0.26
    à¸Ħà¸Ńย
    -0.26
    缸çα
    -0.26
    oulos
    -0.26
    POSITIVE LOGITS
    OR
    0.29
     OR
    0.29
    ets
    0.25
     Orion
    0.24
    (sr
    0.24
    azor
    0.23
    attended
    0.23
    æĢ¥æĢ§
    0.23
     MV
    0.23
    fluence
    0.23
    Activations Density 0.592%

    No Known Activations