© 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. 26101
    Prev
    Next
    INDEX
    Explanations

    second derivative of

    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
    æı´
    -0.10
    wed
    -0.09
    对åѦçĶŁ
    -0.08
    è´²
    -0.08
    éĥģ
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    away
    -0.08
     Tool
    -0.08
    æ³ķåĪ¶
    -0.08
     tool
    -0.08
    POSITIVE LOGITS
    åŃļ
    0.10
    agr
    0.10
    åī§éĻ¢
    0.10
    ç¾¤å²Ľ
    0.09
    æīĭåĨĮ
    0.09
    ç¥ī
    0.09
    æ¯Ĺ
    0.09
    çĭ±
    0.09
    pedia
    0.08
    лоÑĤ
    0.08
    Activations Density 0.005%

    No Known Activations