© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    account login or social account

    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
    æĹłæĦı
    -0.09
    ).__
    -0.08
     Beard
    -0.08
    eldorf
    -0.08
    outu
    -0.08
    _PERMISSION
    -0.08
    æľªç»ıæİĪæĿĥ
    -0.08
     demás
    -0.08
    èĮĦ
    -0.08
    _xt
    -0.08
    POSITIVE LOGITS
    çİ°æľīçļĦ
    0.11
    åİŁæľīçļĦ
    0.11
    èĩªæľī
    0.10
    å¿ĥæĻº
    0.10
    ä¹ĭ声
    0.10
    etes
    0.09
    æīĢæīĢ
    0.09
    å§Ĭ妹
    0.09
    åľ¨æł¡
    0.09
    çĨŁæĤīçļĦ
    0.09
    Activations Density 0.037%

    No Known Activations