© 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. 56320
    Prev
    Next
    INDEX
    Explanations

    company acronyms or prefixes

    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
    auty
    -0.08
    è¿Ļåľº
    -0.08
    usp
    -0.08
     tho
    -0.08
    ä¸ĵ享
    -0.08
    对ä¼ģä¸ļ
    -0.08
    çģ¾
    -0.08
    涯
    -0.07
    çļĦ社ä¼ļ
    -0.07
    MESS
    -0.07
    POSITIVE LOGITS
    åħ¬åı¸
    0.11
     companies
    0.10
    ä¸ĭå±ŀ
    0.10
    巨人
    0.10
    åħ¬åı¸åľ¨
    0.10
    åħ¬åı¸å°Ĩ
    0.10
    è¿Ļ家åħ¬åı¸
    0.10
    æĹ¢æľī
    0.09
    ä¼ŀ
    0.09
    åħ¬åı¸çļĦ
    0.09
    Activations Density 0.170%

    No Known Activations