© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33889
    Prev
    Next
    INDEX
    Explanations

    night

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æĻĴ
    -0.09
    åįĥåı¤
    -0.09
    å¤Ħå¤Ħ
    -0.09
    å¦ĤæĦı
    -0.09
    venues
    -0.09
    Hierarchy
    -0.08
    çļĦæĹ¥åŃIJ
    -0.08
    eter
    -0.08
    çĶĺ
    -0.08
    oner
    -0.08
    POSITIVE LOGITS
    å¤ľéĹ´
    0.14
    å¤ľ
    0.14
    ä¸Ģå¤ľ
    0.14
    -night
    0.12
     overnight
    0.12
     tonight
    0.12
     noct
    0.11
    è¿ŀå¤ľ
    0.11
    ä»ĬæĻļ
    0.11
     ноÑĩ
    0.11
    Activations Density 0.045%

    No Known Activations