© 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. 1731
    Prev
    Next
    INDEX
    Explanations

    don't think

    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
    [element
    -0.10
    èĹIJ
    -0.10
     zwar
    -0.09
    çĸµ
    -0.09
     Bez
    -0.08
    并ä¸İ
    -0.08
    æ«ĥ
    -0.08
    iscard
    -0.08
    ä½łä¹Ł
    -0.08
    驳
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.20
     ever
    0.16
    æľīä»Ģä¹Ī
    0.15
     anything
    0.14
     EVER
    0.13
     anymore
    0.13
     necessarily
    0.12
    ä»»ä½ķ人
    0.12
    anything
    0.12
    ä»»ä½ķå½¢å¼ı
    0.12
    Activations Density 0.044%

    No Known Activations