© 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. 18-TRANSCODER-HP
    7. 88332
    Prev
    Next
    INDEX
    Explanations

    Varied texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     tween
    -0.27
     datatable
    -0.26
    ÊĮ
    -0.26
    tabpanel
    -0.25
    ç¿ļ
    -0.25
    erot
    -0.25
    æĶ¯éħį
    -0.25
    ilian
    -0.24
    åħ±åIJĮåıijå±ķ
    -0.24
    malink
    -0.24
    POSITIVE LOGITS
    äºĽ
    0.28
    mino
    0.26
    æĮĤåľ¨
    0.26
     bulund
    0.26
    æıIJ
    0.25
     fer
    0.25
    æīĵåħ¥
    0.24
    åģ»
    0.24
     rad
    0.24
    .findBy
    0.24
    Activations Density 0.754%

    No Known Activations