© 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. 17003
    Prev
    Next
    INDEX
    Explanations

    herself, himself, yourself

    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
    GRA
    -0.08
    rance
    -0.08
    èĵŁ
    -0.08
    é²Ń
    -0.08
    eeper
    -0.08
     GAM
    -0.08
    amodel
    -0.08
    å½¼æѤ
    -0.08
    ÑīÑĥ
    -0.08
    annel
    -0.08
    POSITIVE LOGITS
    ä¹ĭåŁİ
    0.10
    并åIJij
    0.09
    ìłĪ
    0.09
    æĢį
    0.09
    æĥ®
    0.09
    åı¬
    0.09
    æĬ¥è®°èĢħ
    0.09
    æľĶ
    0.09
     kø
    0.09
    azon
    0.09
    Activations Density 0.029%

    No Known Activations