© 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. 90346
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    åĬĽæ±Ĥ
    -0.30
     Apart
    -0.28
    azer
    -0.27
    身边çļĦ
    -0.27
    BaseContext
    -0.26
    åľ¨çĶŁæ´»ä¸Ń
    -0.26
    Elem
    -0.26
     apart
    -0.25
    jeta
    -0.25
    ypi
    -0.24
    POSITIVE LOGITS
    æ²»çIJĨ
    0.28
     lex
    0.26
     ham
    0.25
    rompt
    0.25
    opup
    0.25
    æĪı
    0.24
     prompt
    0.24
    opp
    0.24
    igation
    0.24
    -time
    0.23
    Activations Density 4.261%

    No Known Activations