© 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. 2241
    Prev
    Next
    INDEX
    Explanations

    saying something

    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
    ä¼ļå¼ķèµ·
    -0.25
    éĢłæĪIJ
    -0.23
    é½IJ
    -0.23
    éĢłæĪIJçļĦ
    -0.23
    fal
    -0.23
    ä¾Ŀæ³ķ追究
    -0.22
     usage
    -0.22
    ä¸įå¦Ĥ
    -0.22
    eryl
    -0.21
    irus
    -0.21
    POSITIVE LOGITS
    æľ¬äºº
    0.28
     Companion
    0.26
    /il
    0.26
     brothers
    0.26
    åıĬåħ¶
    0.25
    让ä»ĸ们
    0.24
    ç»Ļä»ĸ们
    0.23
     Worship
    0.23
    ä¸İåħ¶
    0.23
    èĩªå·±åĸľæ¬¢
    0.23
    Activations Density 0.143%

    No Known Activations