© 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. 9875
    Prev
    Next
    INDEX
    Explanations

    server access

    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
    ä¸Ģæĸ¹
    -0.11
    öt
    -0.10
    lian
    -0.09
    éĢ¼
    -0.09
    èIJ¥
    -0.09
    æķĻç¨ĭ
    -0.09
    rian
    -0.09
    åĶ®åIJİæľįåĬ¡
    -0.09
    æ±ģ
    -0.09
    å¾ħ
    -0.08
    POSITIVE LOGITS
    èĢģçĻ¾å§ĵ
    0.10
    æ¯ı人
    0.09
    åİķ
    0.08
    è¿Ŀ纪
    0.08
    个ä½ĵ
    0.08
    æĶ¿çŃĸ
    0.08
    åľ¨è¿ĩ渡
    0.08
    ConfigurationException
    0.08
    æijĦ
    0.08
    åŃ©åŃIJ们
    0.08
    Activations Density 0.227%

    No Known Activations