© 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. 20261
    Prev
    Next
    INDEX
    Explanations

    good news for

    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
    ä¹ľ
    -0.10
    phony
    -0.09
    п
    -0.08
    æıŃéľ²
    -0.08
    ifu
    -0.08
     Kirst
    -0.08
    éĨĴ
    -0.08
    èµİ
    -0.08
    ench
    -0.08
    就好åĥı
    -0.08
    POSITIVE LOGITS
    好æ¶Īæģ¯
    0.12
    éĤ£äºĽ
    0.11
    åºĶåıĬæŶ
    0.10
    ç¦ıéŁ³
    0.09
    èĨº
    0.09
    åĬłåĢį
    0.09
    幸è¿IJ
    0.09
    ipy
    0.09
    èµĸ以
    0.09
    -END
    0.09
    Activations Density 0.054%

    No Known Activations