© 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. 35-TRANSCODER-HP
    7. 40586
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åįĬ
    -0.50
    half
    -0.39
    n
    -0.34
    ½
    -0.32
    p
    -0.31
    ased
    -0.31
    z
    -0.31
    avi
    -0.30
    e
    -0.30
    azy
    -0.29
    POSITIVE LOGITS
     hut
    0.35
    $h
    0.33
     Hut
    0.32
     \%
    0.31
    _ht
    0.31
    >H
    0.30
     lắm
    0.30
    -HT
    0.30
     huh
    0.30
     hole
    0.30
    Activations Density 4.147%

    No Known Activations