© 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. 57157
    Prev
    Next
    INDEX
    Explanations

    edited or updated information

    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
    åĵī
    -0.11
    æĺ¯ä½ł
    -0.11
    alone
    -0.10
    ä¸ĢéĹª
    -0.10
    åĵĪåĵĪåĵĪ
    -0.10
    æĿµ
    -0.09
    äºĨåIJ§
    -0.09
    åĵĪåĵĪåĵĪåĵĪ
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ä½Ĩä¹Ł
    -0.09
    POSITIVE LOGITS
    ogan
    0.08
    èİ·å¾ĹæĽ´å¤ļ
    0.08
    åĬł
    0.08
    人们对
    0.08
     Worm
    0.07
    atus
    0.07
     podium
    0.07
    éļıçĿĢæŶéĹ´
    0.07
    èİī
    0.07
    specs
    0.07
    Activations Density 0.027%

    No Known Activations