© 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. 35933
    Prev
    Next
    INDEX
    Explanations

    dog breeds or chip

    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
    è·ĭ
    -0.10
    ä¼IJ
    -0.09
    олоÑģ
    -0.09
    èij¡
    -0.09
    æ¼ī
    -0.09
    ä¸Ĭä¸ĭ
    -0.09
    è¶Ĭé«ĺ
    -0.09
    蹬
    -0.08
    èĺij
    -0.08
     beck
    -0.08
    POSITIVE LOGITS
    许
    0.10
     SQLITE
    0.10
    åĴ¬
    0.09
    æĹłæīĢ
    0.09
    лан
    0.08
    apro
    0.08
    quan
    0.08
    çĮ¶
    0.08
    人寿
    0.08
    å®ĥåı¯ä»¥
    0.08
    Activations Density 0.004%

    No Known Activations