© 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. 2428
    Prev
    Next
    INDEX
    Explanations

    voting action

    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
    chy
    -0.24
    åĬŁ
    -0.24
     paren
    -0.23
    æīĵ交éģĵ
    -0.22
     train
    -0.21
    åĬ¨éĿĻ
    -0.21
    éĴŀ
    -0.21
     inve
    -0.21
     manufacture
    -0.21
    stin
    -0.21
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.28
    æĬķ票
    0.27
    /member
    0.26
    /comment
    0.26
    /report
    0.26
    ipse
    0.26
    atform
    0.25
    è¯Ħæ¯Ķ
    0.25
    è¯ĦéĢī
    0.25
    æľ¬ç«Ļ
    0.24
    Activations Density 0.008%

    No Known Activations