© 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. 106953
    Prev
    Next
    INDEX
    Explanations

    Legal cases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å®ļä½į
    -0.31
    Scoped
    -0.27
    åĩ¿
    -0.25
    导åIJij
    -0.25
    åľºåIJĪ
    -0.25
    ãĤıãĤĮãĤĭ
    -0.25
    azy
    -0.25
     scrolled
    -0.24
    optional
    -0.24
    çķĮçļĦ
    -0.24
    POSITIVE LOGITS
    éģº
    0.30
    éģĹ
    0.29
     conflicting
    0.27
    æĭĴä¸į
    0.27
    atte
    0.27
     conflic
    0.26
     flame
    0.26
    å¤ĸåĽ½è¯Ń
    0.26
    å¯ĩ
    0.26
     conflict
    0.25
    Activations Density 1.819%

    No Known Activations