© 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. 23171
    Prev
    Next
    INDEX
    Explanations

    laws breached or violated

    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
     å¼
    -0.09
    è´°
    -0.09
    强è°ĥ
    -0.09
    è¯ģæĺİ
    -0.08
     carn
    -0.08
    -sama
    -0.08
    æĦŁåıĹåĪ°
    -0.08
    ystone
    -0.08
    ä¸Ģæĸ¹
    -0.08
    çĶ¯
    -0.08
    POSITIVE LOGITS
    æŀ¢
    0.09
    宪æ³ķ
    0.09
    å½°
    0.09
    çĮĹ
    0.09
    ROM
    0.09
    æµĭç®Ĺ
    0.09
    躬
    0.08
    æĽĻ
    0.08
    åįłæį®äºĨ
    0.08
    éķĩæĶ¿åºľ
    0.08
    Activations Density 0.042%

    No Known Activations