© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107017
    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
    Negative Logits
    æľ¬å±Ĭ
    -0.28
    å±ĬæŶ
    -0.28
    layui
    -0.26
    åįŁ
    -0.25
    HostException
    -0.25
     mir
    -0.25
    afb
    -0.25
    /lang
    -0.24
    ä¸ĭæīĭ
    -0.24
    ducer
    -0.24
    POSITIVE LOGITS
     rightly
    0.28
    olon
    0.26
    æĻļå¹´
    0.25
     Offline
    0.24
    ç½ij绾ç§ijæĬĢ
    0.24
    æ¼Ĥ亮çļĦ
    0.24
    ä¸īå¹´
    0.24
    èĭķ
    0.24
    åįĹå±±
    0.24
    een
    0.24
    Activations Density 0.553%

    No Known Activations

    This feature has no known activations.