© 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. 32-TRANSCODER-HP
    7. 44155
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    board
    -0.29
    æĸŃ
    -0.28
     ál
    -0.27
     Algorithms
    -0.27
    éķ°
    -0.26
    çĶ»
    -0.26
     moduleName
    -0.25
    forward
    -0.24
     drawn
    -0.24
    éĺ¿å°Ķ
    -0.24
    POSITIVE LOGITS
    po
    0.26
    strup
    0.26
    stands
    0.26
     formal
    0.25
    æŃ£å¼ı
    0.25
    éĻĦå±ŀ
    0.24
     Formal
    0.24
     sourceMappingURL
    0.24
    urring
    0.24
    ÑĪек
    0.24
    Activations Density 0.001%

    No Known Activations