© 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. 20-TRANSCODER-HP
    7. 131039
    Prev
    Next
    INDEX
    Explanations

    Common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Vo
    -0.27
     settled
    -0.25
    proc
    -0.25
    é¡·
    -0.24
    å½±
    -0.24
    æ´²
    -0.24
     dilig
    -0.24
    eur
    -0.24
    éķ«
    -0.24
    erus
    -0.23
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.47
    æĪĸèĢħåħ¶ä»ĸ
    0.45
     or
    0.43
    æĪĸ
    0.39
    æĪĸèĢħ
    0.39
    åıĬåħ¶ä»ĸ
    0.36
    åĴĮåħ¶ä»ĸ
    0.34
    íķĺê±°ëĤĺ
    0.33
    æĪĸæĺ¯
    0.33
    ãģ¾ãģŁãģ¯
    0.33
    Activations Density 69.433%

    No Known Activations