© 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. 61732
    Prev
    Next
    INDEX
    Explanations

    indicating sides or laterality

    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
     Watkins
    -0.11
    åįij
    -0.10
    IMS
    -0.09
     parasite
    -0.09
    èĻļ
    -0.09
    æİ¢
    -0.09
    èĻ«
    -0.08
    æģį
    -0.08
    åĦĴ
    -0.08
    éĤ£äºº
    -0.08
    POSITIVE LOGITS
    èĢ³æľµ
    0.11
    éķIJ
    0.11
    -side
    0.10
     Merr
    0.10
     sides
    0.10
     side
    0.10
    side
    0.10
     ears
    0.09
    ided
    0.09
    好åIJĹ
    0.09
    Activations Density 0.107%

    No Known Activations