© 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. 39624
    Prev
    Next
    INDEX
    Explanations

    Ernest, Ernst, earnest

    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
    ¨
    -0.09
    atan
    -0.09
    pra
    -0.08
    ÄĻ
    -0.08
    ture
    -0.08
    orsch
    -0.08
     اÙĦزÙħÙĨ
    -0.08
    ç¿°
    -0.08
    amp
    -0.08
    åħ¶ä»ĸ人
    -0.08
    POSITIVE LOGITS
    æĥķ
    0.14
    oon
    0.11
    ness
    0.11
    mond
    0.11
    /licenses
    0.10
    è¾Ĩ
    0.10
    ablish
    0.10
    çĶŁç´ł
    0.10
    atively
    0.09
    è¾ĺ
    0.09
    Activations Density 0.019%

    No Known Activations