© 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. 19512
    Prev
    Next
    INDEX
    Explanations

    reading and related activities

    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
    çij
    -0.09
    åIJµ
    -0.08
    èĪª
    -0.08
    ä¹IJéĺŁ
    -0.08
    笨
    -0.08
    éĤ´
    -0.08
    ç«ĻçĿĢ
    -0.08
     Gün
    -0.08
     Constraints
    -0.08
    erving
    -0.08
    POSITIVE LOGITS
    人éĢī
    0.11
    äºĨ大éĩıçļĦ
    0.10
    hof
    0.10
    çŀij
    0.10
    æıIJæĹ©
    0.09
    éĶIJ
    0.09
    æıIJåīį
    0.09
    éĸ±è®Ģ
    0.09
    èĨĺ
    0.09
    -light
    0.09
    Activations Density 0.056%

    No Known Activations