© 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. 2108
    Prev
    Next
    INDEX
    Explanations

    time of day

    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
    åŃĺåľ¨éĹ®é¢ĺ
    -0.27
    è¯ģåĪ¸æĬķèµĦ
    -0.26
    æĬ¤èº«
    -0.26
    åħ¨åĮº
    -0.26
    åŃĺåľ¨çļĦ
    -0.24
    rowable
    -0.24
    åĮºåĨħ
    -0.24
     hurd
    -0.24
    ä¸ŃåŃĺåľ¨çļĦ
    -0.23
     persisted
    -0.23
    POSITIVE LOGITS
    -ish
    0.32
    æĹ©æĻ¨
    0.32
    åĤįæĻļ
    0.32
     early
    0.32
    æĹ©ä¸Ĭ
    0.30
     evening
    0.30
    åįĬå¤ľ
    0.30
     evenings
    0.30
     late
    0.29
    åĩĮæĻ¨
    0.28
    Activations Density 0.018%

    No Known Activations