© 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. 61743
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    Ậ
    -0.10
    ä¸į失
    -0.09
    妥
    -0.09
    PELL
    -0.09
    åħ¶å®ŀå°±æĺ¯
    -0.09
    ski
    -0.08
    代表æĢ§
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
    ssel
    -0.08
    epochs
    -0.08
    POSITIVE LOGITS
    çľĭæĿ¥
    0.13
     judging
    0.13
    æĿ¥çľĭ
    0.12
    æĥħåĨµæĿ¥çľĭ
    0.12
    jud
    0.11
    åı¯ä»¥çľĭåĩº
    0.11
    ä¸Ģçľĭ
    0.11
    迹象
    0.11
    æł·åŃIJ
    0.10
    çľĭåĩº
    0.10
    Activations Density 0.097%

    No Known Activations