© 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. 27-TRANSCODER-HP
    7. 9716
    Prev
    Next
    INDEX
    Explanations

    say "h" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -Ta
    -0.27
    éĴµ
    -0.25
    容å¿į
    -0.25
    emu
    -0.25
    æºī
    -0.25
    çĻĮ
    -0.24
    éĢī举
    -0.24
    ROY
    -0.24
    ä¸įå®Į
    -0.24
    森æŀĹ
    -0.23
    POSITIVE LOGITS
     hyper
    0.49
    hyper
    0.48
    h
    0.47
    hf
    0.38
    hh
    0.36
    han
    0.34
     Hyper
    0.34
    hs
    0.34
    hx
    0.33
    _hyper
    0.33
    Activations Density 0.002%

    No Known Activations