© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38018
    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/qwen3-32b-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
    é¢ģå¥ĸ
    -0.09
    ycin
    -0.09
    _MALLOC
    -0.09
    漪
    -0.09
    _CYCLE
    -0.09
    çĶŁæ´»çݯå¢ĥ
    -0.09
    ä¸Ĭ级
    -0.08
     tá»ī
    -0.08
    UTILITY
    -0.08
    _hz
    -0.08
    POSITIVE LOGITS
    ä»ķ
    0.12
    ä¸ĭåįĪ
    0.10
    angs
    0.10
     hour
    0.10
     ä¸ĭåįĪ
    0.10
    åĪ·
    0.10
     afternoon
    0.09
    æĹ¶æ®µ
    0.09
    åįĬå°ıæŶ
    0.09
    Direct
    0.09
    Activations Density 0.060%

    No Known Activations