© 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. 9936
    Prev
    Next
    INDEX
    Explanations

    surgical resection and reconstruction

    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
    æįº
    -0.09
     term
    -0.08
    IRD
    -0.08
    çľ¼çľĭ
    -0.08
    actively
    -0.08
    vern
    -0.08
     Bans
    -0.08
    æµĭ
    -0.08
    .manual
    -0.08
    注å°Ħ
    -0.08
    POSITIVE LOGITS
    å¤ĸç§ij
    0.11
    ä¿ĿçķĻ
    0.11
    åĪĩéĻ¤
    0.11
    ä¿Ŀä½ı
    0.10
    åĿ¼
    0.09
    çļĦåģļæ³ķ
    0.09
    CISION
    0.09
    é«ĺä½į
    0.09
     Surge
    0.09
    æī¿åĬŀ
    0.09
    Activations Density 0.796%

    No Known Activations