© 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. 9-TRANSCODER-HP
    7. 30203
    Prev
    Next
    INDEX
    Explanations

    thermal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mult
    -0.30
    åı¤èĢģçļĦ
    -0.28
    ä¸ĸ代
    -0.27
    çĨ¨
    -0.27
    èµ°ä¸Ĭ
    -0.27
    ois
    -0.26
    ilateral
    -0.26
    ifu
    -0.26
    æľīæĿĥ
    -0.25
     olds
    -0.25
    POSITIVE LOGITS
    usercontent
    0.30
    berger
    0.29
    iya
    0.26
     Yayın
    0.26
    éĢģåĩº
    0.25
    anoia
    0.25
    mani
    0.24
     fick
    0.24
    else
    0.23
     Rosenstein
    0.23
    Activations Density 0.264%

    No Known Activations