© 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. 44235
    Prev
    Next
    INDEX
    Explanations

    six

    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
     eight
    -0.28
    åħ«
    -0.28
    8
    -0.26
    åħ«å¹´
    -0.26
    -eight
    -0.26
    ohen
    -0.25
    åħ«åįģ
    -0.25
    /providers
    -0.25
     Ink
    -0.25
     eighty
    -0.24
    POSITIVE LOGITS
     sixth
    0.41
     Six
    0.38
     six
    0.38
     Sixth
    0.37
     SIX
    0.36
    6
    0.36
    -six
    0.35
    åħŃ个
    0.35
    第åħŃ
    0.33
    Six
    0.32
    Activations Density 0.012%

    No Known Activations