© 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. 58274
    Prev
    Next
    INDEX
    Explanations

    works have been selected or found

    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
    pars
    -0.11
    产åĵģçłĶåıij
    -0.10
    inky
    -0.09
    森
    -0.09
    æīij
    -0.09
     ourselves
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.09
    æī¿åĬŀ
    -0.09
    ä¸ĭæĿ¥çļĦ
    -0.09
    æĬĢæľ¯åĪĽæĸ°
    -0.09
    POSITIVE LOGITS
    èİ«åIJį
    0.09
    ãģįãģ£ãģĭãģij
    0.09
    è¯Ħ为
    0.09
    rne
    0.08
    éĶĢ
    0.08
    å¤ļ次
    0.08
    åľ¨åħ¨åĽ½
    0.08
    åĩŃä»Ģä¹Ī
    0.08
    常常
    0.08
    æīĢåľ¨åľ°
    0.08
    Activations Density 0.097%

    No Known Activations