© 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. 109207
    Prev
    Next
    INDEX
    Explanations

    code and calculations

    np_max-act-logits · gemini-2.0-flash
    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
    æ¼Ķ
    -0.29
     radix
    -0.28
    åħļçļĦ建设
    -0.26
    NodeType
    -0.25
    å«£
    -0.24
    _system
    -0.24
    度
    -0.24
    è¾ĵäºĨ
    -0.24
    ä¸īæľŁ
    -0.23
    èĻIJå¾ħ
    -0.23
    POSITIVE LOGITS
    achi
    0.28
    adesh
    0.27
    Light
    0.27
    åħīæºIJ
    0.26
    æĿ¡
    0.26
     lighting
    0.26
    åħīæĺİ
    0.26
     opportunities
    0.25
    ewater
    0.24
    ifi
    0.24
    Activations Density 0.934%

    No Known Activations