© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30831
    Prev
    Next
    INDEX
    Explanations

    some of the

    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
    éĩįè§Ĩ
    -0.09
    istas
    -0.09
    建çŃijçī©
    -0.08
    æłı
    -0.08
    åħ³æĢĢ
    -0.08
    å¼ķãģį
    -0.08
    åįģ足
    -0.08
    æĵį
    -0.08
    èı©æıIJ
    -0.08
    æĸ¯åŁº
    -0.08
    POSITIVE LOGITS
     ÑģобÑĢан
    0.10
    ç½ijåıĭè¯Ħ论
    0.09
    åĤ¾
    0.09
    åħīçħ§
    0.09
    lassian
    0.09
    å¾Ģå¹´
    0.09
    -times
    0.09
    öz
    0.09
    çĶļèĩ³æĺ¯
    0.08
    åħļåĴĮæĶ¿åºľ
    0.08
    Activations Density 0.038%

    No Known Activations