© 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. 3627
    Prev
    Next
    INDEX
    Explanations

    struggling and battling

    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
    éģĤ
    -0.09
    åģı好
    -0.08
    ä¹ĺ车
    -0.08
    å¢Ł
    -0.08
    Fel
    -0.08
    ç¨Ķ
    -0.08
    èĩ§
    -0.07
    æ¼ł
    -0.07
     consumer
    -0.07
    _rm
    -0.07
    POSITIVE LOGITS
    æĮ£æīİ
    0.22
     struggle
    0.17
    äºī夺
    0.15
    寻æī¾
    0.14
     struggles
    0.14
    èĭ¦èĭ¦
    0.14
     struggling
    0.14
    çºłç»ĵ
    0.14
    äºīåıĸ
    0.13
    è¯ķåĽ¾
    0.13
    Activations Density 0.089%

    No Known Activations