© 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. 107562
    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
     gate
    -0.26
    apeut
    -0.26
     ,[
    -0.25
    åħ¨æĸĩ
    -0.24
    azon
    -0.24
    æĿ¥çļĦ
    -0.24
    (___
    -0.24
    ctal
    -0.23
    ież
    -0.23
    arnation
    -0.23
    POSITIVE LOGITS
    é«Ģ
    0.25
     subclasses
    0.24
    ä¸ĢçĤ¹
    0.24
     Dip
    0.24
    ä¸į足以
    0.24
     visual
    0.24
    arged
    0.23
    _Man
    0.23
    è¯Ħ为
    0.23
    hip
    0.23
    Activations Density 0.994%

    No Known Activations

    This feature has no known activations.