© 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. 23695
    Prev
    Next
    INDEX
    Explanations

    future generation

    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
    羿
    -0.10
    é¹Ĭ
    -0.10
    ç»Ļ大家
    -0.09
    ä½łåºĶ该
    -0.09
    çĨ
    -0.09
     streak
    -0.08
    大家åı¯ä»¥
    -0.08
    åıijå¸ĥ
    -0.08
    大家
    -0.08
    让大家
    -0.08
    POSITIVE LOGITS
    ä¸ĭä¸Ģ代
    0.24
    æľªæĿ¥çļĦ
    0.22
    æľªæĿ¥
    0.19
    å°ĨæĿ¥
    0.18
    æľªä¾Ĩ
    0.18
     future
    0.17
    æľªæĿ¥åıijå±ķ
    0.17
    åIJİå¤ĩ
    0.15
    åIJİ代
    0.15
    å¹´è½»
    0.15
    Activations Density 0.057%

    No Known Activations