© 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. 21592
    Prev
    Next
    INDEX
    Explanations

    parenthesized lists

    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
    bite
    -0.10
    ajes
    -0.09
    üsü
    -0.09
    allas
    -0.09
    æĪ´
    -0.08
    _rom
    -0.08
    ensex
    -0.08
    osas
    -0.08
     surfing
    -0.08
    æ±Ł
    -0.08
    POSITIVE LOGITS
    /or
    0.10
    or
    0.10
     heavyweight
    0.08
    bo
    0.08
    åĩºè·¯
    0.08
    on
    0.08
    ç¡Ŀ
    0.08
    ç¼ĵç¼ĵ
    0.07
    åĸĥ
    0.07
    èĪģ
    0.07
    Activations Density 0.282%

    No Known Activations