© 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. 40654
    Prev
    Next
    INDEX
    Explanations

    liter

    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
    itionally
    -0.31
    æ¼ł
    -0.30
    nowled
    -0.30
    tempts
    -0.30
    ogeneous
    -0.29
    IMUM
    -0.28
    verages
    -0.28
    itional
    -0.28
    oriously
    -0.28
    обÑħодим
    -0.27
    POSITIVE LOGITS
    bew
    0.32
    aby
    0.30
     Sey
    0.29
    eli
    0.28
    GH
    0.28
    aine
    0.28
    se
    0.27
     Ill
    0.27
    uur
    0.27
    bell
    0.26
    Activations Density 0.345%

    No Known Activations