© 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. 43998
    Prev
    Next
    INDEX
    Explanations

    something was recorded/seen

    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
    -formed
    -0.30
    icol
    -0.28
     Saved
    -0.27
     Prepared
    -0.26
    -fed
    -0.26
     Fed
    -0.26
     strcmp
    -0.26
    æĮ¤
    -0.26
    aved
    -0.25
    fed
    -0.25
    POSITIVE LOGITS
     recorded
    0.34
     seen
    0.32
     apparent
    0.32
    æĿ¡è¯Ħ论
    0.31
     reported
    0.30
     encountered
    0.30
     demonstrated
    0.29
    >(()
    0.29
     documented
    0.28
     evident
    0.27
    Activations Density 0.014%

    No Known Activations