© 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. 2296
    Prev
    Next
    INDEX
    Explanations

    spent most of his/her life

    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
    åĢĴæĺ¯
    -0.23
    å¼ĩ
    -0.23
     spar
    -0.22
     comparator
    -0.22
    dit
    -0.21
    è°ģçŁ¥
    -0.21
    ENE
    -0.21
    ico
    -0.20
     key
    -0.20
     Continental
    -0.19
    POSITIVE LOGITS
    è¿Ļ段æŶéĹ´
    0.34
    æŶéĹ´
    0.32
    段æŶéĹ´
    0.30
     time
    0.30
    æĻĤéĸĵ
    0.30
    æ²īæµ¸åľ¨
    0.29
    å¿ĥæĢĿ
    0.29
     nights
    0.28
    æĹ¥åľ¨
    0.28
    ç²¾åĬĽ
    0.27
    Activations Density 0.041%

    No Known Activations