© 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. 24-TRANSCODER-HP
    7. 150306
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     banker
    -0.27
    UDA
    -0.26
    饱åĴĮ
    -0.25
    çĬĩ
    -0.24
    ä¼Ĭæĸ¯
    -0.24
    ç»ĻåĬĽ
    -0.24
    èĥį
    -0.24
    ãĤ¸ãĥ¥
    -0.24
    ropol
    -0.23
     '<%=
    -0.23
    POSITIVE LOGITS
    è¿IJ
    0.30
     inf
    0.29
    åİĺ
    0.28
    è°ĥ
    0.26
    bindings
    0.26
     prelim
    0.25
    æİ¥åıĹ
    0.25
     af
    0.24
     inform
    0.24
     LayoutInflater
    0.24
    Activations Density 0.642%

    No Known Activations

    This feature has no known activations.