© 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. 21674
    Prev
    Next
    INDEX
    Explanations

    "Sure" followed by continuation

    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
    ç½ijå°ıç¼ĸ
    -0.11
    ACE
    -0.10
    ä¹ĭæīĢ以
    -0.10
    inspace
    -0.09
    éĿŀ常éĩįè¦ģ
    -0.09
    羣å¿ĥ
    -0.09
    asts
    -0.09
    éĿŀ常çļĦ
    -0.09
    Enumerator
    -0.09
    ä¸įåĨįæĺ¯
    -0.08
    POSITIVE LOGITS
    åľ¨çĶŁæ´»ä¸Ń
    0.09
    overlap
    0.09
    ëĭ´
    0.08
    pon
    0.08
    _REFER
    0.08
    BUM
    0.08
    gross
    0.08
    erer
    0.08
    itable
    0.08
    elder
    0.08
    Activations Density 0.005%

    No Known Activations