© 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. 107062
    Prev
    Next
    INDEX
    Explanations

    Foreign characters

    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
    Negative Logits
    大家
    -0.43
     you
    -0.42
    æĪij们
    -0.41
     we
    -0.40
    æĤ¨
    -0.36
    åĴ±ä»¬
    -0.35
    ä½łä»¬
    -0.34
    ä½łåľ¨
    -0.33
     everyone
    -0.33
     мÑĭ
    -0.33
    POSITIVE LOGITS
    åľ¨ä»ĸçļĦ
    0.26
    -Re
    0.25
     denn
    0.25
    ius
    0.25
    äºĨä»ĸçļĦ
    0.24
    代
    0.24
     named
    0.24
    _MPI
    0.24
    .ErrorCode
    0.23
    PullParser
    0.23
    Activations Density 1.029%

    No Known Activations