© 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. 62659
    Prev
    Next
    INDEX
    Explanations

    the set of

    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
    çİĦ
    -0.08
    åĨ³ä¸į
    -0.08
    åħ¥åºĵ
    -0.08
    è¿Ļæĺ¯æĪij
    -0.08
    çijķ
    -0.08
    群ä½ĵ
    -0.07
    鼶
    -0.07
     Associates
    -0.07
    iaux
    -0.07
     Hollow
    -0.07
    POSITIVE LOGITS
    åĪĪ
    0.10
    (CH
    0.09
    æĥ³äºĨæĥ³
    0.09
    å¸ĪèĮĥ
    0.09
     ÑģкаÑĩ
    0.09
    cych
    0.09
    åķ¤
    0.09
    ìį¨
    0.09
    绾
    0.09
    ëį°ìĿ´
    0.09
    Activations Density 0.599%

    No Known Activations