© 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. 38824
    Prev
    Next
    INDEX
    Explanations

    as or so comparisons

    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
    éģ
    -0.09
    æİ¢
    -0.09
    eh
    -0.09
    ven
    -0.09
    0
    -0.08
    è´¯
    -0.08
    æľĪåĪĿ
    -0.08
    å¥Ħ
    -0.08
    vc
    -0.08
     lifting
    -0.08
    POSITIVE LOGITS
    æķŀ
    0.11
    éĤĢ
    0.10
    ompiler
    0.10
    ä½Ĩä»į
    0.09
    extent
    0.09
    _PC
    0.09
    éĤ£ä¹Ī容æĺĵ
    0.09
    PAIR
    0.08
    alis
    0.08
    utow
    0.08
    Activations Density 0.032%

    No Known Activations