© 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. 40603
    Prev
    Next
    INDEX
    Explanations

    Being active

    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
    active
    -0.66
    Active
    -0.65
     Active
    -0.65
    	active
    -0.61
     active
    -0.60
    -active
    -0.60
    _active
    -0.59
    (active
    -0.59
     setActive
    -0.56
    .active
    -0.53
    POSITIVE LOGITS
     appropriately
    0.28
     spit
    0.27
     conveniently
    0.27
     intox
    0.27
     interact
    0.27
     smoothly
    0.26
    èģĶ绾
    0.26
    å°ıå°ı
    0.25
     correctly
    0.25
     subt
    0.25
    Activations Density 6.241%

    No Known Activations