© 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. 58106
    Prev
    Next
    INDEX
    Explanations

    whether 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
    Ñģид
    -0.10
    ãģĵãĤĮãĤī
    -0.09
    çĵł
    -0.09
    好人
    -0.09
    itte
    -0.09
    åįī
    -0.08
    åĨĻäºĨ
    -0.08
    ç²¾ç¥ŀçĹħ
    -0.08
    åīįèĢħ
    -0.08
    agh
    -0.08
    POSITIVE LOGITS
    éĹ³
    0.09
    _shadow
    0.08
    èģĶç½ij
    0.08
    ä¸Ģ缴
    0.08
    æĽ´å¤ļçļĦæĺ¯
    0.08
    ä¸ĢæŃ¥
    0.08
    éĹ°
    0.08
    æݥ触
    0.08
    åĨ³ä¸į
    0.08
    çļĦä¸ĢäºĽ
    0.08
    Activations Density 0.034%

    No Known Activations