© 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. 6847
    Prev
    Next
    INDEX
    Explanations

    wouldn't / not followed by coordinating or negative auxiliaries

    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
    BOSE
    -0.10
    pite
    -0.10
    è¿ĺæľª
    -0.09
    ãĥĵãĤ¸
    -0.09
    ãģĦãģ¾ãģĽãĤĵ
    -0.09
    tesy
    -0.09
    穷人
    -0.09
     Steele
    -0.09
    ä»įæľª
    -0.08
    ä¼ļ导èĩ´
    -0.08
    POSITIVE LOGITS
    æĶ¾å¿ĥ
    0.09
    orsk
    0.09
    æĿŁ
    0.09
    ahu
    0.08
    iani
    0.08
    æ²IJæµ´
    0.08
    ram
    0.08
    ansi
    0.08
    ro
    0.08
    shaw
    0.08
    Activations Density 0.012%

    No Known Activations