© 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. 141774
    Prev
    Next
    INDEX
    Explanations

    Technology and information

    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
    ä¾Ľç»Ļ侧
    -0.29
    ·¨
    -0.28
    memberOf
    -0.27
    ycin
    -0.27
    =-=-
    -0.27
    InputBorder
    -0.27
    æĪĸæĺ¯
    -0.26
    isque
    -0.25
    è¶ħåĩº
    -0.25
    rowad
    -0.24
    POSITIVE LOGITS
    ç¬ŀ
    0.29
    Und
    0.27
     Und
    0.27
    оÑı
    0.26
     und
    0.26
    god
    0.25
    _DESC
    0.25
    Directed
    0.24
    еÑģÑĤв
    0.24
    ifica
    0.23
    Activations Density 17.205%

    No Known Activations