© 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. 56116
    Prev
    Next
    INDEX
    Explanations

    cooking and computing commands

    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
    å®ŀåľ¨
    -0.09
    unik
    -0.09
    çħŀ
    -0.09
    åı¶åŃIJ
    -0.09
    æŁĶ软
    -0.09
    éļıæŶéļıåľ°
    -0.08
    å·²å®ĮæĪIJ
    -0.08
    对ä¸įèµ·
    -0.08
    æīĪ
    -0.08
     Marin
    -0.08
    POSITIVE LOGITS
    éĹª
    0.10
    çī
    0.09
    çĥĻ
    0.09
    éĶij
    0.08
    éĸĥ
    0.08
     fry
    0.08
    roperty
    0.08
    IDGE
    0.08
    å·¥ç¨ĭè´¨éĩı
    0.08
    墩
    0.08
    Activations Density 0.012%

    No Known Activations