© 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. 30-TRANSCODER-HP
    7. 94900
    Prev
    Next
    INDEX
    Explanations

    temperature

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -SA
    -0.29
    é¦Ļ
    -0.28
    缴å¾Ħ
    -0.28
     Lim
    -0.26
    ÅŁim
    -0.25
    温度
    -0.25
    æĿī
    -0.25
    æłijæľ¨
    -0.25
     Sunderland
    -0.25
    Spl
    -0.24
    POSITIVE LOGITS
    igate
    0.28
    edImage
    0.28
     tou
    0.26
    عÙĨ
    0.26
    plate
    0.26
     plates
    0.26
     collapsed
    0.26
     plate
    0.25
    aceous
    0.25
    è¦ģåĬłå¼º
    0.25
    Activations Density 0.099%

    No Known Activations