© 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. 52630
    Prev
    Next
    INDEX
    Explanations

    The

    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
    西çıŃ
    -0.10
    atsu
    -0.10
    åIJĦç§įåIJĦæł·
    -0.09
    Ùİا
    -0.09
    ⽤
    -0.09
     Fleet
    -0.09
    èĢģçĪ¸
    -0.09
    Ãłng
    -0.09
    æIJ´
    -0.09
    åĨįåĬłä¸Ĭ
    -0.09
    POSITIVE LOGITS
    oris
    0.09
    æĹ©æĹ©
    0.08
    ench
    0.08
    éĢļãĤĬ
    0.08
    ä¹İ
    0.08
    Ñıм
    0.08
    riott
    0.08
    ÑĩаÑĤ
    0.08
    å¿Ļç¢Į
    0.08
    裤
    0.08
    Activations Density 0.020%

    No Known Activations