© 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. 899
    Prev
    Next
    INDEX
    Explanations

    pokémon collection

    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
    ams
    -0.11
    olf
    -0.10
    ä¸įè¿ľ
    -0.09
    å§ij
    -0.09
    ä¸Ģåı·
    -0.09
    ä¸įéĹ´
    -0.08
    èĩº
    -0.08
    ä¸įçĽ¸ä¿¡
    -0.08
    RIX
    -0.08
    éĺī
    -0.08
    POSITIVE LOGITS
    æ³¥
    0.11
    æŃ£å®Ĺ
    0.10
    åį¡çīĩ
    0.09
    Collect
    0.09
    æ¾³
    0.09
     collecting
    0.09
    _Collections
    0.09
    èĥĮéĿ¢
    0.09
     backing
    0.09
    æĬ¼
    0.09
    Activations Density 0.085%

    No Known Activations