© 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. 56836
    Prev
    Next
    INDEX
    Explanations

    oh yeah!

    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
    нак
    -0.09
    kinson
    -0.08
    avana
    -0.08
    terra
    -0.08
    ideal
    -0.08
    æĢ¼
    -0.08
    ulis
    -0.08
    èĩªæŁ¥
    -0.08
    ä¸Ģçľ¼
    -0.07
    æĪ¿è½¦
    -0.07
    POSITIVE LOGITS
    缸åħ³æĸ°éĹ»
    0.09
    hlen
    0.09
    ALSE
    0.09
    æĬĬæĪij
    0.09
    éĴµ
    0.09
    ç¾İ好çĶŁæ´»
    0.09
    ÑģоÑĢ
    0.08
    å¼ĢåѦ
    0.08
    躲éģ¿
    0.08
    èķĥ
    0.08
    Activations Density 0.007%

    No Known Activations