© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1965
    Prev
    Next
    INDEX
    Explanations

    instructional content and material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Destructor
    -0.23
    æīĢ示
    -0.22
    ä¸įå°ıå¿ĥ
    -0.22
    èµ°å¾Ĺ
    -0.22
     Exact
    -0.20
     Nice
    -0.20
    aval
    -0.20
     Bret
    -0.20
    åĽ¢è´Ń
    -0.20
    åģļ人
    -0.19
    POSITIVE LOGITS
    ìľ¡
    0.27
    åĴĮæĶ¯æĮģ
    0.25
    Assistant
    0.24
     Woodward
    0.24
    andre
    0.24
    /render
    0.23
    诲
    0.23
    è¿ĩç¨ĭä¸Ń
    0.23
    è¿ĩç¨ĭ
    0.23
    orado
    0.22
    Activations Density 0.008%

    No Known Activations