© 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. 141797
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    åĪ¶
    -0.27
     Peb
    -0.27
    以ä¸ĭç®Ģ称
    -0.26
    ãģ¾ãģĻãģĮ
    -0.26
    å¤įæĿĤçļĦ
    -0.26
    å¤įæĿĤ
    -0.26
    åIJį
    -0.25
    æ±ĩçİĩ
    -0.24
    opath
    -0.24
    称
    -0.24
    POSITIVE LOGITS
    ä¸įåģľåľ°
    0.29
    ä»Ķç»Ĩ
    0.28
    atty
    0.28
    dı
    0.27
     inverse
    0.27
    ä¸įåģľçļĦ
    0.26
    .Sdk
    0.25
    isches
    0.25
     onCreate
    0.25
     quotient
    0.24
    Activations Density 3.322%

    No Known Activations