© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 35144
    Prev
    Next
    INDEX
    Explanations

    daily life and dissatisfaction

    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
    æİĸ
    -0.10
    ä¸ĵå®¶ç»Ħ
    -0.09
    ucs
    -0.09
    æ³Ħæ¼ı
    -0.08
    éĺ²æ±Ľ
    -0.08
    æįİ
    -0.08
    饥饿
    -0.08
    çīĩéĿ¢
    -0.08
    åħ¬åħ±åľºæīĢ
    -0.08
    å¼Łå¼Ł
    -0.08
    POSITIVE LOGITS
    ç¢Į
    0.14
    å¹³åĩ¡
    0.12
    ä¸į满æĦı
    0.12
    çĶŁæ´»
    0.11
    éº»æľ¨
    0.11
    éĩįå¤į
    0.11
    çϽé¢Ĩ
    0.10
    梦æĥ³
    0.10
    庸
    0.10
    æĹ¥åŃIJ
    0.10
    Activations Density 0.085%

    No Known Activations