© 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. 58861
    Prev
    Next
    INDEX
    Explanations

    Boston Celtics

    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
    éĤ£ç§į
    -0.09
    çĺ¿
    -0.09
    éŀij
    -0.09
    ODO
    -0.09
    éĩijèŀįå¸Ĥåľº
    -0.09
    å½±åĵįåĬĽçļĦ
    -0.09
    åĺĽ
    -0.09
    ä¸Ģå°ģä¿¡
    -0.08
    æ²®
    -0.08
     mund
    -0.08
    POSITIVE LOGITS
    æ·
    0.10
    åIJĮä¸Ģ
    0.09
    çĪ¶åŃIJ
    0.09
    èĬĹ
    0.09
    retch
    0.08
    olph
    0.08
    isi
    0.08
    å¸ĪçĶŁ
    0.08
    alion
    0.07
    cls
    0.07
    Activations Density 0.016%

    No Known Activations