© 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. 30-TRANSCODER-HP
    7. 95220
    Prev
    Next
    INDEX
    Explanations

    digestion, glucose, metabolism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    offline
    -0.28
    åı²ä¸Ĭ
    -0.27
    lim
    -0.26
    Prov
    -0.26
    _probs
    -0.26
    Offline
    -0.26
    Founder
    -0.26
    éĻĤ
    -0.25
    æ»ļ
    -0.25
    头çĸ¼
    -0.25
    POSITIVE LOGITS
     deliver
    0.33
     delivered
    0.33
    交ä»ĺ
    0.33
    è°ĥèĬĤ
    0.32
    andle
    0.32
     delivery
    0.32
     entreg
    0.30
    'util
    0.30
     regulate
    0.30
     usage
    0.30
    Activations Density 0.002%

    No Known Activations