© 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. 1832
    Prev
    Next
    INDEX
    Explanations

    melanoma or mitomycin

    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
     chá»Ĺ
    -0.10
    ä¸Ģ家人
    -0.09
    raj
    -0.08
    éĶ´
    -0.08
     Lung
    -0.08
    对人ä½ĵ
    -0.08
    è´¤
    -0.08
    æŁ´
    -0.08
    æĺ§
    -0.08
     Lager
    -0.08
    POSITIVE LOGITS
    çĿ«
    0.11
    ocular
    0.11
    çļĦçľ¼
    0.11
    çľ¼éĥ¨
    0.10
    æĴķ
    0.10
    éĻ¨
    0.10
    潸
    0.09
    è¿ijè§Ĩ
    0.09
    çľ¼ç§ij
    0.09
    箪
    0.09
    Activations Density 0.604%

    No Known Activations