© 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. 23-TRANSCODER-HP
    7. 25263
    Prev
    Next
    INDEX
    Explanations

    code/text artifacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     main
    -0.29
    erman
    -0.26
     radix
    -0.26
    _main
    -0.25
     dig
    -0.24
    主è¦ģ
    -0.24
     healing
    -0.24
    .main
    -0.24
     slack
    -0.23
     blinded
    -0.23
    POSITIVE LOGITS
    ä¸įæİĴéĻ¤
    0.32
    çļĦé£İéĻ©
    0.32
    é£İéĻ©
    0.30
    æĥħåĨµ
    0.30
    åIJĪçIJĨçļĦ
    0.28
    EXPECTED
    0.28
    é«ĺ度
    0.27
     caution
    0.27
    åIJĪçIJĨ
    0.27
    æĭŃ
    0.27
    Activations Density 0.001%

    No Known Activations