© 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. 5850
    Prev
    Next
    INDEX
    Explanations

    club meetings and activities

    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
    èļĮ
    -0.10
    ç¾¹
    -0.09
    _HOT
    -0.09
    æıIJæĭĶ
    -0.09
    holm
    -0.09
    éĹ´æİ¥
    -0.09
    ä¸ĢåŃĹ
    -0.09
    .hot
    -0.08
     ÑĢазмеÑīен
    -0.08
     анг
    -0.08
    POSITIVE LOGITS
    ç¤¾åĽ¢
    0.13
    ä¼ļåijĺ
    0.10
    åħ´è¶£
    0.10
    èĪĪ趣
    0.10
    çĪ±å¥½èĢħ
    0.10
    ä¸įå®ļ
    0.09
    æľīåħ´è¶£
    0.09
    çĪ±å¥½
    0.09
    群
    0.09
    社群
    0.09
    Activations Density 0.097%

    No Known Activations