© 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. 2932
    Prev
    Next
    INDEX
    Explanations

    classified ads and advertising

    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
    对å¤ĸ
    -0.09
    raid
    -0.08
    å®£ä¼ł
    -0.08
    anity
    -0.08
    æīĵåĩ»
    -0.07
     McB
    -0.07
    _cached
    -0.07
     اÙĦØ°
    -0.07
    shutdown
    -0.07
    arden
    -0.07
    POSITIVE LOGITS
    è¿Ļä¹Ł
    0.11
    mts
    0.10
    .yahoo
    0.10
    å¦Ļ
    0.09
    ÑīиÑĤ
    0.09
    Svc
    0.09
    çļĦä¸ĢéĿ¢
    0.09
    èıĢ
    0.09
    æľīæĿ¡ä»¶
    0.09
    ismic
    0.09
    Activations Density 0.003%

    No Known Activations