© 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. 57284
    Prev
    Next
    INDEX
    Explanations

    neurological crisis

    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
    æĸĹ
    -0.12
    ogan
    -0.09
    chein
    -0.09
    çIJµ
    -0.09
    cene
    -0.09
    æĪijä¼ļ
    -0.09
    eldo
    -0.09
    èijij
    -0.09
    igy
    -0.09
    æ¶ij
    -0.08
    POSITIVE LOGITS
    åıĹåĪ°äºĨ
    0.09
    åIJĥ饱
    0.09
    èĩ´åĬĽ
    0.09
    太å¤ļäºĨ
    0.08
    ç¥ŀè¯Ŀ
    0.08
    æŁIJç§į
    0.08
    è¿ĩäºİ
    0.08
    oct
    0.08
    å¸ĮèħĬ
    0.08
    éļĶéŁ³
    0.08
    Activations Density 0.078%

    No Known Activations