© 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. 61111
    Prev
    Next
    INDEX
    Explanations

    talking about or needing help

    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
     enrich
    -0.08
    ä½IJ
    -0.08
    æĿ¥èĩª
    -0.08
    å¯Įæľī
    -0.08
    amo
    -0.08
    èIJ½åľ¨
    -0.08
    åĩºäºİ
    -0.08
    yle
    -0.08
    çĥ¦æģ¼
    -0.07
    htag
    -0.07
    POSITIVE LOGITS
    è¿ĻéĩĮ
    0.26
     here
    0.25
    åľ¨è¿ĻéĩĮ
    0.25
    è¿ĻåĦ¿
    0.24
    è¿ĻéĩĮæľī
    0.22
    éĢĻ裡
    0.22
     здеÑģÑĮ
    0.21
    è¿ĻéĩĮæĺ¯
    0.21
     ÙĩÙĨا
    0.21
    è¿ĻéĩĮçļĦ
    0.20
    Activations Density 0.117%

    No Known Activations