© 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. 38883
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Not in Any Lists

    No Comments

    Negative Logits
    (ins
    -1.62
     Ins
    -1.60
    Ins
    -1.59
    ins
    -1.58
    -ins
    -1.57
    _ins
    -1.53
    .ins
    -1.45
     ins
    -1.45
    INS
    -1.40
     INS
    -1.40
    POSITIVE LOGITS
     aromatic
    0.28
    ariat
    0.27
     aroma
    0.25
     atlas
    0.25
     arom
    0.25
     atmospheric
    0.25
     atmosphere
    0.23
    osphere
    0.23
    arning
    0.23
    allas
    0.23
    Activations Density 7.334%

    No Known Activations