© 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. 52535
    Prev
    Next
    INDEX
    Explanations

    working for

    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
    arence
    -0.10
    éķ¿èĢģ
    -0.09
    秦çļĩ
    -0.09
    修身
    -0.08
    å°ij女
    -0.08
    éĥ¨åĪĨåľ°åĮº
    -0.08
    ç§Ģ
    -0.08
     resid
    -0.08
    大巴
    -0.08
    è¿Ļä¹Łæĺ¯
    -0.08
    POSITIVE LOGITS
    /pay
    0.10
    éªŀ
    0.09
    ussen
    0.08
    CTOR
    0.08
    ä¸Ģæĸ¹
    0.08
    åĬ¨çĶŁæĪIJ
    0.08
    Boss
    0.08
    æĶ¿åºľéĥ¨éŨ
    0.08
    形容
    0.08
    _nth
    0.08
    Activations Density 0.054%

    No Known Activations