© 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. 90197
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ''↵
    -0.28
    -definition
    -0.28
    æĺ¯ä»ĸ
    -0.28
    olla
    -0.27
     tq
    -0.26
    åIJĴ
    -0.26
     tob
    -0.25
    capabilities
    -0.25
    éĹ®ä»ĸ
    -0.24
    recursive
    -0.24
    POSITIVE LOGITS
    iner
    0.27
    éľ¾
    0.26
     scl
    0.26
    端åįĪ
    0.26
     cor
    0.26
    æ°ijæĹı
    0.26
    çļĦæķ°éĩı
    0.25
    æĪĸèĢħåħ¶ä»ĸ
    0.25
    AL
    0.24
    aways
    0.24
    Activations Density 8.932%

    No Known Activations