© 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. 6523
    Prev
    Next
    INDEX
    Explanations

    the season

    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
    çİ°è´§
    -0.09
     prat
    -0.09
    壳
    -0.09
    izando
    -0.08
    iza
    -0.08
    atz
    -0.08
    ä¸Ńå¤ĸ
    -0.08
    çݳ
    -0.08
     Bhar
    -0.08
    uo
    -0.08
    POSITIVE LOGITS
    æĪĸèĢħ说
    0.10
    ter
    0.09
    æĪij们åºĶ该
    0.09
    PED
    0.09
    åIJĮç±»
    0.09
     ниÑĩ
    0.09
    æĪij们认为
    0.08
    æĪij们çļĦ
    0.08
    ä¸Ģ个个
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    Activations Density 0.017%

    No Known Activations