© 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. 22123
    Prev
    Next
    INDEX
    Explanations

    depends/hinges 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
    é£Ł
    -0.09
    бÑĢоÑģ
    -0.09
    æĬ½
    -0.09
    ç³Ĭæ¶Ĥ
    -0.08
    磨
    -0.08
    éĵŃ
    -0.08
    峡
    -0.08
    ç¯ĩ
    -0.08
    год
    -0.08
    ç®Ģ
    -0.08
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.19
    æĪIJè´¥
    0.16
    èĥ½åIJ¦
    0.15
    åıĸåĨ³
    0.15
     depends
    0.14
    ä¾Ŀèµĸ
    0.14
     завиÑģиÑĤ
    0.13
    å¾Ī大ç¨ĭ度
    0.13
    好åĿı
    0.13
    çļĦåħ³éĶ®
    0.12
    Activations Density 0.079%

    No Known Activations