© 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. 58640
    Prev
    Next
    INDEX
    Explanations

    birds or bird names

    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
    æİĪ
    -0.10
    ä¼½
    -0.09
    æłij
    -0.08
    ords
    -0.08
    quent
    -0.08
    jax
    -0.08
    åĴĮä»ĸçļĦ
    -0.08
    çºł
    -0.08
    Alg
    -0.08
    illi
    -0.08
    POSITIVE LOGITS
    ä¸Ģæŀ¶
    0.09
    æ³¥åľŁ
    0.09
    éŀĭåŃIJ
    0.09
    æľĢåħĪè¿ĽçļĦ
    0.09
    lessly
    0.09
     Watt
    0.08
    åķ¼
    0.08
    ä¸įå¿ĺ
    0.08
    æĺ¨
    0.08
    çĶŁç´ł
    0.08
    Activations Density 0.034%

    No Known Activations