© 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. 54202
    Prev
    Next
    INDEX
    Explanations

    time or date context

    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°±æĺ¯è¿Ļæł·
    -0.11
    åĪ°æľŁ
    -0.10
    åĩłå¹´åīį
    -0.09
    åīįåĩłå¹´
    -0.09
    éªĪ
    -0.09
    çĵľ
    -0.09
    åįģå¹´åīį
    -0.08
     ÃŃch
    -0.08
    ASF
    -0.08
    å²Į
    -0.08
    POSITIVE LOGITS
    åIJĮæĹ¶ä¹Łæĺ¯
    0.11
    å·½
    0.10
    åĪ¶æĪIJ
    0.10
     biç
    0.09
    alog
    0.09
    å±ĬæŶ
    0.09
    æĭ¢
    0.09
    èĪī
    0.08
    亲
    0.08
    _REV
    0.08
    Activations Density 0.083%

    No Known Activations