© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50989
    Prev
    Next
    INDEX
    Explanations

    New York cities and universities

    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
    西å®īå¸Ĥ
    -0.11
    éĥijå·ŀå¸Ĥ
    -0.11
    æĪIJéĥ½å¸Ĥ
    -0.10
    æ½¼
    -0.10
    åįĹå®ģå¸Ĥ
    -0.10
    西æ¹ĸ
    -0.10
    åľ¨å¹¿å·ŀ
    -0.10
    西å®ī
    -0.10
     Melbourne
    -0.10
    èĵī
    -0.10
    POSITIVE LOGITS
     Syracuse
    0.14
     Rochester
    0.12
    æī¿å¾·
    0.11
     Cornell
    0.10
     Scho
    0.09
    erty
    0.09
    postgres
    0.09
     Niagara
    0.09
     Vermont
    0.08
    çİīç±³
    0.08
    Activations Density 0.123%

    No Known Activations