© 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. 64366
    Prev
    Next
    INDEX
    Explanations

    mathematical/technical notation

    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
     purpose
    -0.29
    缮çļĦ
    -0.28
    oure
    -0.26
    婵
    -0.26
     purposes
    -0.25
     ASC
    -0.25
    å¾ĹçĽĬ
    -0.25
     sui
    -0.24
    eses
    -0.24
    çļĦåIJĦ项
    -0.24
    POSITIVE LOGITS
    é³Į
    0.24
    rão
    0.24
     mapStateToProps
    0.23
    kt
    0.23
    å¥ĺ
    0.23
    èĶĵ
    0.23
    _DEFINE
    0.23
    æŃ»åIJİ
    0.23
    ickle
    0.22
     обоÑĢ
    0.22
    Activations Density 15.218%

    No Known Activations