© 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. 37534
    Prev
    Next
    INDEX
    Explanations

    US cities and states

    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
     Carnegie
    -0.09
     Cah
    -0.09
    MSN
    -0.08
    ç©·
    -0.08
    THR
    -0.08
    æıIJåĪ°
    -0.08
    ç¿ł
    -0.08
    å¼ºåĽ½
    -0.08
    åĨĻåŃĹ
    -0.08
    æĢĻ
    -0.08
    POSITIVE LOGITS
    鼶è·Ŀ离
    0.09
     MPG
    0.09
    åIJĦéĥ¨éŨ
    0.09
    æľºåħ³
    0.09
    æľ½
    0.09
    ä¸İä¼Ĺ
    0.09
     transgender
    0.09
    享
    0.09
    .GetObject
    0.09
    æĶ¿åºľ
    0.08
    Activations Density 0.021%

    No Known Activations