© 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. 10574
    Prev
    Next
    INDEX
    Explanations

    here

    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
    iant
    -0.10
    çķĮ
    -0.10
    orb
    -0.09
    çĩ®
    -0.08
    ä¸Ģä½ĵ
    -0.08
    笺
    -0.08
    è¯ĹæĦı
    -0.08
    RA
    -0.08
    æĺİæĺİ
    -0.08
    Ex
    -0.07
    POSITIVE LOGITS
    æĥ¯
    0.13
    comed
    0.10
    湯
    0.09
    ä¼ı
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    ARGS
    0.09
    åĹľ
    0.09
    æĭľ
    0.09
    enders
    0.09
    ä¸Ģå¥Ĺ
    0.09
    Activations Density 0.035%

    No Known Activations