© 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. 19538
    Prev
    Next
    INDEX
    Explanations

    like or love

    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
    太éĺ³åŁİ
    -0.09
    ensis
    -0.09
    çĬĬ
    -0.08
    åı«å£°
    -0.08
     cocos
    -0.08
    ä¸įå¾Ĺ转载
    -0.08
     giấc
    -0.08
    æĪijä¸įæĥ³
    -0.08
    Translations
    -0.08
    éĢ£çºĮ
    -0.08
    POSITIVE LOGITS
    squ
    0.09
    ä¸įå·²
    0.08
    仲
    0.08
    ulously
    0.08
    çĨı
    0.08
     finding
    0.08
    åģļä¸ĢäºĽ
    0.08
     è§
    0.08
    çľģåĨħ
    0.08
    èĤ¢ä½ĵ
    0.08
    Activations Density 0.030%

    No Known Activations