© 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. 107640
    Prev
    Next
    INDEX
    Explanations

    Code, documentation, or articles

    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
    AndView
    -0.30
    .defer
    -0.24
    ãģŃãģĩ
    -0.24
    FLAG
    -0.24
    (collection
    -0.24
    xac
    -0.24
    _FOREACH
    -0.24
    æĪijãģĮ
    -0.23
    祯
    -0.23
     WHILE
    -0.23
    POSITIVE LOGITS
    äºĺ
    0.29
    以ä¸Ĭ
    0.29
    ont
    0.28
    äºĴ
    0.26
    èĩªè´¸
    0.25
    ç´§å¼ł
    0.25
    触æij¸
    0.25
    æīĪ
    0.24
    座è°Ī
    0.24
    oric
    0.24
    Activations Density 0.649%

    No Known Activations