© 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. 2060
    Prev
    Next
    INDEX
    Explanations

    clothing descriptions

    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
    æĽ´æľī
    -0.29
     delightful
    -0.27
    æĹ¨åľ¨
    -0.27
    æ¯ıä¸Ģ次
    -0.26
     delicious
    -0.26
    æŨ
    -0.26
     marvel
    -0.26
     revital
    -0.25
    æ¯ıä¸Ģ
    -0.25
    æ¯ıä¸Ģä½į
    -0.24
    POSITIVE LOGITS
     unidentified
    0.36
     possibly
    0.32
    ä½ľæ¡Ī
    0.29
    éķ¿çº¦
    0.28
     identifiable
    0.28
     Likely
    0.28
     headlights
    0.28
    ä¸į认è¯Ĩ
    0.28
    伪è£ħ
    0.27
     unspecified
    0.27
    Activations Density 0.017%

    No Known Activations