© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    unicorn, Pinterest, design

    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
    ç»ŀ
    -0.09
    游æĪıå½ĵä¸Ń
    -0.09
    adel
    -0.09
    å©¿
    -0.09
    ç¼ĺåĪĨ
    -0.08
    èIJİ
    -0.08
    Ĥ¬
    -0.08
    è¯ķçĤ¹å·¥ä½ľ
    -0.08
    轨
    -0.08
    .gif
    -0.07
    POSITIVE LOGITS
    强çĥĪ
    0.10
    褶
    0.10
    çŀ¬éĹ´
    0.09
     Accord
    0.09
    æŁIJ个
    0.09
    æ¸ħæĻ¨
    0.09
    èĹIJ
    0.09
    волÑĮ
    0.08
    ç´łæĿIJ
    0.08
    强çĥĪçļĦ
    0.08
    Activations Density 0.072%

    No Known Activations