© 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. 27-TRANSCODER-HP
    7. 7856
    Prev
    Next
    INDEX
    Explanations

    formal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    icorn
    -0.26
    .DAY
    -0.26
    è¡¥åħħ
    -0.25
    ·æĸ°
    -0.25
     actual
    -0.24
     outright
    -0.24
    Days
    -0.24
    ering
    -0.24
    urs
    -0.24
    ViewItem
    -0.23
    POSITIVE LOGITS
    dehyde
    0.40
    ize
    0.34
    ised
    0.32
    ized
    0.30
    izes
    0.27
    è¿ĻæŶ
    0.25
    azed
    0.25
    ities
    0.25
    isms
    0.25
    iz
    0.24
    Activations Density 0.007%

    No Known Activations