© 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. 35865
    Prev
    Next
    INDEX
    Explanations

    voluntarily surrendered or came forward

    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
     Mystic
    -0.09
    缴è§Ĥ
    -0.09
    å½¹
    -0.09
    èIJ¥åĪ©
    -0.09
    å·¡åĽŀ
    -0.09
    åĴĦ
    -0.09
    asts
    -0.08
    fil
    -0.08
    æĺ¥åŃ£
    -0.08
    .ToInt
    -0.08
    POSITIVE LOGITS
    åħij
    0.12
    主åĭķ
    0.11
    äºĨèĩªå·±çļĦ
    0.11
    主åĬ¨
    0.10
    éĶĴ
    0.09
    Ñİ
    0.09
    ä»Ģä¹Īæł·
    0.09
    æ¿ij
    0.09
    locator
    0.09
    äºĨä¸Ģæī¹
    0.09
    Activations Density 0.014%

    No Known Activations