© 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. 2707
    Prev
    Next
    INDEX
    Explanations

    file, platforms, systems, app, gland, sheets, team, food

    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
    æĥħåĨµè¿Ľè¡Į
    -0.10
    ç§įç§į
    -0.10
    éĤ£å°±æĺ¯
    -0.10
    èĢĮæĺ¯
    -0.10
    èĢĮä¸Ķè¿ĺ
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    æīĢè°ĵ
    -0.09
    æĬĢæľ¯åĴĮ
    -0.09
    ä»ĸå°±
    -0.09
    POSITIVE LOGITS
    ä¹ŁåĽłæѤ
    0.15
    èĻ½
    0.13
    åĪĻ
    0.12
    èĻ½çĦ¶
    0.12
    åĽºçĦ¶
    0.11
    ä¸įä»ħ
    0.11
    å§ĭç»Ī
    0.11
     ëĺIJíķľ
    0.11
    æ¯ı天éĥ½
    0.10
    ç¡®å®ŀ
    0.10
    Activations Density 2.226%

    No Known Activations