© 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. 22364
    Prev
    Next
    INDEX
    Explanations

    on

    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
    æ±Łå±±
    -0.09
    åĩºåıij
    -0.09
    åľĪåŃIJ
    -0.09
    鸾
    -0.09
    æĭħ
    -0.08
    ạ
    -0.08
    é«ĺåħ´
    -0.08
    éĹ·
    -0.08
    ä¸ĢåĿĹ
    -0.08
    çĶ¨æīĭ
    -0.08
    POSITIVE LOGITS
     on
    0.11
    伦çIJĨ
    0.10
    æĸ½
    0.10
    身ä¸Ĭ
    0.10
    èĢ¸
    0.10
    дÑĢ
    0.09
    磾
    0.09
    æŶå°ļ
    0.09
    è¿ĩçļĦ
    0.09
    eon
    0.08
    Activations Density 0.269%

    No Known Activations