© 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. 58219
    Prev
    Next
    INDEX
    Explanations

    never done anything

    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
    è¾ŀ
    -0.09
    ä¸įèĩ³äºİ
    -0.08
    _INST
    -0.08
    æĪ¾
    -0.08
    ssi
    -0.08
    çĮľæĥ³
    -0.08
    ows
    -0.08
    æģ¨ä¸įå¾Ĺ
    -0.08
    äºĨåĩł
    -0.08
    æ¯ı个æľĪ
    -0.08
    POSITIVE LOGITS
    ä¹ĭåīį
    0.13
    以åīį
    0.11
    è¿Ļä¹Ī大
    0.10
    æľīè¿ĩ
    0.10
    ä¹ĭåīįçļĦ
    0.10
    ç»ıåİĨè¿ĩ
    0.10
    áĢĨ
    0.10
    ä»»ä½ķ
    0.10
    ä¸ĭæīĭ
    0.10
    anything
    0.10
    Activations Density 0.072%

    No Known Activations