© 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. 51106
    Prev
    Next
    INDEX
    Explanations

    activity

    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声
    -0.10
    æĿ³
    -0.09
    ä¼ļè®®ä¸Ĭ
    -0.09
    ãĢħ
    -0.09
    lei
    -0.08
     kn
    -0.08
    å¹³åı°ä¸Ĭ
    -0.08
    ä¸Ĭæľī
    -0.08
    éŨå¤ĸ
    -0.08
     dereg
    -0.08
    POSITIVE LOGITS
     ÑĢабоÑĤÑĥ
    0.11
    аÑĨиÑİ
    0.10
    ÑĨиÑİ
    0.10
    angkan
    0.10
     ÑģвоÑİ
    0.09
     ÑģÑĥммÑĥ
    0.09
    æijĦå½±ä½ľåĵģ
    0.09
    ancer
    0.09
    ÅĽÄĩ
    0.09
    ning
    0.09
    Activations Density 0.065%

    No Known Activations