© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21006
    Prev
    Next
    INDEX
    Explanations

    special recognition and praise

    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
     Zw
    -0.10
    Mine
    -0.09
    夹
    -0.09
    iente
    -0.08
    å½ķåıĸ
    -0.08
    åıĹåΰ影åĵį
    -0.08
    éĻĽä¸ĭ
    -0.08
    ëĿ¼ëıĦ
    -0.08
    éªļæī°
    -0.08
    ilder
    -0.08
    POSITIVE LOGITS
    弯
    0.09
    æıĨ
    0.09
    èĬĤåģĩæĹ¥
    0.09
    æĦŁ
    0.08
    alers
    0.08
    Girl
    0.08
    æ¶Ľ
    0.08
    걸
    0.08
    éĴİ
    0.08
    inson
    0.08
    Activations Density 0.023%

    No Known Activations