© 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. 21058
    Prev
    Next
    INDEX
    Explanations

    not to

    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
    æĭIJ
    -0.09
    åīĶ
    -0.09
    cth
    -0.09
    irit
    -0.09
     пÑĢид
    -0.09
    صÙĦØ©
    -0.09
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.09
    åĽŀé¦ĸ
    -0.08
    éĵ®
    -0.08
    祯
    -0.08
    POSITIVE LOGITS
    ork
    0.11
    æĦī
    0.09
    åıĹåĪ°äºĨ
    0.09
    åŁ´
    0.09
    使åħ¶
    0.09
    åıĹåĪ°
    0.09
    æĪijä¸įæĥ³
    0.08
    æĺ¯éĿŀ
    0.08
     Cah
    0.08
    ä¸į让
    0.08
    Activations Density 0.105%

    No Known Activations