© 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. 6722
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    æĹĹå¸ľ
    -0.10
    sWith
    -0.10
    æĦŁåºĶ
    -0.09
    æĸĵ
    -0.09
    anda
    -0.08
    è¡ħ
    -0.08
    uario
    -0.08
    å®°
    -0.08
     ãĢĮ
    -0.08
    ç«ĭãģ¡
    -0.08
    POSITIVE LOGITS
    åģı
    0.10
     Occ
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
    å¾Īæ·±
    0.09
    ypi
    0.09
    æĬ¿
    0.09
    èħ°
    0.08
    æ¡Ĥ
    0.08
    ffset
    0.08
    å«Ĥ
    0.08
    Activations Density 0.008%

    No Known Activations