© 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. 10848
    Prev
    Next
    INDEX
    Explanations

    future events

    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
    ä»Ĭ年以æĿ¥
    -0.09
    çŁŃçŁŃ
    -0.09
    ç³ľ
    -0.09
    è¾ĥä½İ
    -0.09
    agher
    -0.09
    åİŁæľī
    -0.09
    åīįä¸ī
    -0.09
    è·µ
    -0.09
    以人æ°ij
    -0.09
    Esc
    -0.08
    POSITIVE LOGITS
    æľªæĿ¥çļĦ
    0.17
    å°ĨæĿ¥
    0.14
     someday
    0.14
    æľªæĿ¥
    0.14
     future
    0.14
    åľ¨æľªæĿ¥
    0.13
    ä¸ĭä¸Ģ代
    0.13
    future
    0.13
     eventually
    0.12
    ä»ĬåIJİ
    0.12
    Activations Density 0.427%

    No Known Activations