© 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. 6478
    Prev
    Next
    INDEX
    Explanations

    career development opportunities

    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
    çĤ¹æ»´
    -0.09
    uka
    -0.08
    æľĢä½³
    -0.08
    æŁIJç§į
    -0.08
    åłĩ
    -0.08
    çļĦä¸Ģç§į
    -0.08
    çķıæĥ§
    -0.08
    çķĽ
    -0.08
    åı²ä¸Ĭ
    -0.08
    aily
    -0.08
    POSITIVE LOGITS
    æģ¯
    0.11
    æİ¥ä¸ĭæĿ¥
    0.10
     новоÑģÑĤи
    0.10
    ä¸įéĶĻçļĦ
    0.10
    å¼Ģå±Ģ
    0.09
     overall
    0.09
    ç§ī
    0.09
    ÑģпоÑĢ
    0.09
     Samar
    0.09
    å¼Ģ端
    0.09
    Activations Density 0.156%

    No Known Activations