© 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. 25522
    Prev
    Next
    INDEX
    Explanations

    Number "3" and related symbols

    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
    Negative Logits
    cript
    -0.30
    ulaire
    -0.26
    cir
    -0.25
    åĴª
    -0.25
    IBC
    -0.25
    姥姥
    -0.25
    one
    -0.24
    StyleSheet
    -0.24
    нÑģкой
    -0.23
    æĬĢæľ¯åĴĮ
    -0.23
    POSITIVE LOGITS
    upo
    0.33
    lash
    0.29
    authors
    0.27
    ?f
    0.25
    __).
    0.24
    affles
    0.24
    çīµå¤´
    0.24
     contributors
    0.23
     credited
    0.23
    gart
    0.23
    Activations Density 1.199%

    No Known Activations