© 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. 20143
    Prev
    Next
    INDEX
    Explanations

    grant applications, research proposals

    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
    许åı¯è¯ģ
    -0.09
    arda
    -0.09
    pcf
    -0.08
    rait
    -0.08
    _PERMISSION
    -0.08
     qualities
    -0.08
     grads
    -0.08
    é£Ĵ
    -0.08
    èĢĥè¯ģ
    -0.08
    .Screen
    -0.08
    POSITIVE LOGITS
    æĮij
    0.10
    裤
    0.09
    èIJĨ
    0.09
    åIJįå¸Ī
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
    ä¸įåĪ©äºİ
    0.09
     اÙĦعÙĦÙħ
    0.09
    å°ıçĭĹ
    0.08
    æ°ijå¿ĥ
    0.08
     science
    0.08
    Activations Density 0.117%

    No Known Activations