© 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. 108484
    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
    çĶ¨æĪ·æıIJä¾Ľ
    -0.30
    管å±Ģ
    -0.29
    干货
    -0.28
    osas
    -0.28
    /misc
    -0.27
    工信
    -0.27
    à¹Ĥà¸Ļ
    -0.27
    åİŁæĸĩåľ°åĿĢ
    -0.26
    anh
    -0.26
     internally
    -0.26
    POSITIVE LOGITS
    SURE
    0.31
    贪婪
    0.28
     glu
    0.27
    liches
    0.25
    çľ¯
    0.24
    IDD
    0.24
    BAR
    0.24
    饥
    0.24
    GIN
    0.24
    RAP
    0.24
    Activations Density 0.933%

    No Known Activations

    This feature has no known activations.