© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29421
    Prev
    Next
    INDEX
    Explanations

    unofficial / informal

    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
    Negative Logits
    HF
    -0.10
    pes
    -0.09
    icket
    -0.09
    éľ²
    -0.09
    ivity
    -0.09
    大äºĭ
    -0.09
    è¿Ń
    -0.09
    èĻ±
    -0.08
    iska
    -0.08
    _latency
    -0.08
    POSITIVE LOGITS
    ently
    0.10
    éĹ²
    0.09
    èĩªåıij
    0.09
    ç§ģèĩª
    0.09
    along
    0.09
    egan
    0.09
    沿
    0.09
    æĬ¿
    0.08
    å¤ľéĹ´
    0.08
     à¹Ĩ
    0.08
    Activations Density 0.020%

    No Known Activations