© 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. 25-TRANSCODER-HP
    7. 109032
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recom
    -0.26
    exampleInput
    -0.26
    è¦ĨçĽĸçİĩ
    -0.25
    ãģ£ãģĵ
    -0.24
     functools
    -0.24
     Norris
    -0.24
     ([[
    -0.23
    rire
    -0.23
    vette
    -0.23
    urch
    -0.23
    POSITIVE LOGITS
    æĮ¥
    0.32
    åIJ¯åıij
    0.30
    æĪ³
    0.28
    Jimmy
    0.28
    æĺĵ
    0.27
    ala
    0.26
    èĥ½å¤Ł
    0.26
    åģľæ»ŀ
    0.26
    ienen
    0.25
    æĪIJ为
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.