© 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. 20-TRANSCODER-HP
    7. 108769
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĮ¿åIJį
    -0.28
    ibs
    -0.28
    举
    -0.27
    å¦Ĥæŀľæľī
    -0.26
    éĤ£äºĽ
    -0.26
    adj
    -0.25
    åij³
    -0.25
     adj
    -0.24
    unt
    -0.24
    olic
    -0.24
    POSITIVE LOGITS
    æĹ©åľ¨
    0.30
    tracker
    0.27
     ExecutionContext
    0.27
    äºĨä¸Ģ份
    0.26
    æĭ¨
    0.26
    pread
    0.26
    .linspace
    0.25
    baz
    0.25
    .initState
    0.24
    ä¸Ģä¸ĩ
    0.24
    Activations Density 7.026%

    No Known Activations