© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10368
    Prev
    Next
    INDEX
    Explanations

    as to

    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
    .Zip
    -0.09
    ParallelGroup
    -0.09
    天天
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
     Regents
    -0.09
    ì¤ijìķĻ
    -0.08
    CloseOperation
    -0.08
    æĥŁ
    -0.08
    楷
    -0.08
    idual
    -0.08
    POSITIVE LOGITS
    符
    0.10
    å¾Ĺ好
    0.09
    åĪ°åºķ
    0.08
    å¢ŀæĶ¶
    0.08
    fol
    0.08
    razier
    0.08
    为ä½ķ
    0.08
    ç¦ıçī¹
    0.08
    åĪ°åºķæĺ¯
    0.07
    è¿Ļä¹Łæĺ¯
    0.07
    Activations Density 0.052%

    No Known Activations