© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37283
    Prev
    Next
    INDEX
    Explanations

    to followed by verb

    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
    æ¥Ķ
    -0.11
    éĤ£ä¸ĢåĪ»
    -0.10
    æľĢåĪĿçļĦ
    -0.10
    à¹Ĥà¸Ĭ
    -0.09
    -relative
    -0.09
    åİŁæĿ¥çļĦ
    -0.09
    èĩ´çĶµ
    -0.09
    夫人
    -0.09
    éľĸ
    -0.09
    æ´Ĺ礼
    -0.09
    POSITIVE LOGITS
    oton
    0.09
    oyo
    0.08
    gard
    0.08
    ä¸įæĪIJ
    0.08
    ylon
    0.08
    ãģĮãģĭ
    0.08
    ä¸ĩåĪĨ
    0.08
    parable
    0.07
    rush
    0.07
     Tate
    0.07
    Activations Density 0.020%

    No Known Activations