© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9512
    Prev
    Next
    INDEX
    Explanations

    something else

    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
    çķ
    -0.09
    çĥŃçĪ±
    -0.09
     بÙĬ
    -0.08
     Nack
    -0.08
    ANI
    -0.08
     Rim
    -0.08
    çĺª
    -0.08
    åħ³å¿ĥ
    -0.08
    è´¿èµĤ
    -0.08
    çħħ
    -0.08
    POSITIVE LOGITS
    é¾Ł
    0.10
    åĽĽä¸ªæĸ¹éĿ¢
    0.09
    建ç«ĭ
    0.09
    èijµ
    0.09
    横åIJij
    0.09
    empo
    0.08
    èµ°ä¸ĭåİ»
    0.08
    æ¶īæ¡Ī
    0.08
    æ¥Ķ
    0.08
    æĸĩ书
    0.08
    Activations Density 0.019%

    No Known Activations