© 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. 22-TRANSCODER-HP
    7. 87005
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    fare
    -0.27
    eos
    -0.27
    å«Ĥ
    -0.27
    åĽĽæĺ¯
    -0.26
     Traditional
    -0.26
    æĸ°éĽ¶åĶ®
    -0.25
    _strerror
    -0.24
    otto
    -0.24
    ä¹Łå°±æĺ¯
    -0.24
    enis
    -0.23
    POSITIVE LOGITS
    西路
    0.27
    西
    0.26
    åıĺ
    0.25
     zh
    0.25
    ób
    0.25
    idy
    0.25
     tie
    0.24
    åĴĮè°IJ
    0.24
     past
    0.24
    宾客
    0.24
    Activations Density 0.009%

    No Known Activations