© 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. 108275
    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
    gh
    -0.28
     rez
    -0.25
    çļĦè¯Ŀ
    -0.25
     compatibility
    -0.24
     des
    -0.24
    å°±ä¸ļå²Ĺä½į
    -0.24
    åĩıå¼±
    -0.24
    innie
    -0.24
    å·¥ä½ľæķĪçİĩ
    -0.23
    AP
    -0.23
    POSITIVE LOGITS
     puff
    0.26
    Ẫ
    0.26
    个å¤ļ
    0.25
    éĤ¸
    0.25
     Assistance
    0.25
    pk
    0.25
     viá»ĩn
    0.25
     poke
    0.24
    nk
    0.24
    ç¿ħ
    0.24
    Activations Density 0.931%

    No Known Activations

    This feature has no known activations.