© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35990
    Prev
    Next
    INDEX
    Explanations

    anti-

    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
    ä¸Ģ个èģĮä¸ļ
    -0.11
     minut
    -0.09
    indi
    -0.09
    è£ģ
    -0.09
    å°º
    -0.09
     neutr
    -0.09
    骸
    -0.09
    operand
    -0.09
    çĽ¥
    -0.09
     ÐłÐ¾
    -0.09
    POSITIVE LOGITS
    éĺ²æŃ¢
    0.11
    çĥ¦
    0.09
    orsk
    0.08
    æݪæĸ½
    0.08
    ä½ıäºĨ
    0.08
    çĻŀ
    0.08
    çŃĸ
    0.08
    æļ´
    0.08
    éķij
    0.08
    磷
    0.08
    Activations Density 0.140%

    No Known Activations