© 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. 14-TRANSCODER-HP
    7. 39693
    Prev
    Next
    INDEX
    Explanations

    Loss of consciousness/fainting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _partitions
    -0.28
    æĥĺ
    -0.26
    çĿ£å¯Ł
    -0.26
    çģ¯åħī
    -0.25
     Geo
    -0.24
     Nag
    -0.24
     member
    -0.23
    appen
    -0.23
    -strong
    -0.23
    LOC
    -0.23
    POSITIVE LOGITS
    WORD
    0.27
    width
    0.26
    宽度
    0.26
     jakie
    0.26
    acula
    0.26
    æĸ¥
    0.25
    wort
    0.25
    æ¦Ń
    0.25
    yahoo
    0.24
    请æķĻ
    0.24
    Activations Density 1.006%

    No Known Activations