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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 156
    Prev
    Next
    INDEX
    Explanations

    small groups, May to June

    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
     smarter
    -0.41
     folks
    -0.39
     DIY
    -0.36
     ведÑĮ
    -0.35
     smart
    -0.34
     savvy
    -0.34
    æ¯Ķå¦Ĥ
    -0.34
    ç²¾åĩĨ
    -0.33
     kids
    -0.33
    ï¸ı
    -0.33
    POSITIVE LOGITS
    游æĪı代
    0.40
     Ä°sl
    0.40
    使çĶ¨ç¶²è·¯
    0.40
    åľ¨çݩ家ä¸Ń
    0.38
    游æĪıåī¯æľ¬
    0.37
    æĪĸå¤ļæĪĸ
    0.36
    æĸ°äººçݩ家
    0.36
    åºĶçĶ¨æŁ¥çľĭ
    0.36
     markedly
    0.34
     заÑĢегиÑģÑĤ
    0.34
    Activations Density 0.445%

    No Known Activations