© 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. 49087
    Prev
    Next
    INDEX
    Explanations

    group 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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ī项
    -0.12
    çĶ·æľĭåıĭ
    -0.10
    æ»ĭåij³
    -0.09
    _sizes
    -0.09
    å±Ģå±Ģéķ¿
    -0.09
    å¸Ĥå§Ķ书记
    -0.09
    åıĮèĦļ
    -0.09
    女æľĭåıĭ
    -0.09
    еÑĩ
    -0.09
     ÙħÙĪÙĤÙģ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ群
    0.18
    è¿Ļ群
    0.12
    åıijæī¬
    0.09
    ä¹ı
    0.09
    çľĭ好
    0.09
    ừa
    0.09
    angelo
    0.09
    çļĦæĺ¯
    0.08
     bunch
    0.08
    ä¸Ģæī¹
    0.08
    Activations Density 0.093%

    No Known Activations