© 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. 35-TRANSCODER-HP
    7. 39857
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Variables
    -0.27
    thur
    -0.26
    ä¸ĢæĿ¡é¾Ļ
    -0.26
     nond
    -0.26
     poll
    -0.25
     unrecognized
    -0.25
    zelf
    -0.24
    oteric
    -0.24
     Starr
    -0.24
    ä½Ĩæĺ¯åľ¨
    -0.24
    POSITIVE LOGITS
    rott
    0.26
    åĢĴ
    0.26
    æľĢä½İ
    0.25
    Conf
    0.24
    æļĩ
    0.24
    io
    0.24
    ç²¾ç¥ŀ
    0.23
    ']}'
    0.23
    æĢ¼
    0.23
    3
    0.23
    Activations Density 2.374%

    No Known Activations

    This feature has no known activations.