© 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. 33403
    Prev
    Next
    INDEX
    Explanations

    login or register

    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
    æ·¦
    -0.11
    讲课
    -0.10
    寥
    -0.09
    annot
    -0.09
    èĢĥä¸Ĭ
    -0.09
    é«ĺæĢ§èĥ½
    -0.09
    ANNOT
    -0.09
     ÑĨелÑĮÑİ
    -0.09
    å°Ħæīĭ
    -0.09
    æįİ
    -0.09
    POSITIVE LOGITS
    auce
    0.09
    оÑĢÑĤ
    0.09
     ÑĤек
    0.08
    rouch
    0.08
    èıĬèĬ±
    0.08
     acab
    0.08
    溯æºIJ
    0.08
     Fors
    0.08
    è¹Ī
    0.08
    端æŃ£
    0.08
    Activations Density 0.003%

    No Known Activations