© 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. 53127
    Prev
    Next
    INDEX
    Explanations

    specific file clauses

    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
    åŁºæľ¬æĥħåĨµ
    -0.10
     ÑģобÑģÑĤвенно
    -0.09
    ä¸ĢåĪĩ
    -0.09
    åŁºæľ¬ä¿¡æģ¯
    -0.09
     bare
    -0.08
    æѧ
    -0.08
    ermo
    -0.08
    æĦ¦
    -0.08
    岫
    -0.08
    åIJĦæĸ¹
    -0.08
    POSITIVE LOGITS
     конкÑĢеÑĤ
    0.13
    çī¹å®ļ
    0.11
    specific
    0.11
    ä¸ĵ
    0.11
    -specific
    0.11
    éĴĪ对
    0.11
    -purpose
    0.10
     specific
    0.10
    èĪ
    0.10
     Specific
    0.09
    Activations Density 0.261%

    No Known Activations