© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9130
    Prev
    Next
    INDEX
    Explanations

    ruins and rubble

    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
    å¾·æĭī
    -0.10
    åİŁåĪĽ
    -0.09
    çķĮ
    -0.09
    诳
    -0.09
    éĹ¾
    -0.09
    çİĭåħĪçĶŁ
    -0.08
    ä¸Ģ头
    -0.08
    olis
    -0.08
    çķĮçļĦ
    -0.08
    uffles
    -0.08
    POSITIVE LOGITS
    æ®ĭ
    0.17
    æ¯ģ
    0.15
     wreckage
    0.14
    çł´æįŁ
    0.14
    çł´ç¢İ
    0.14
    æįŁåĿı
    0.14
    æ®ĭçķĻ
    0.14
     debris
    0.13
    æ®ĺ
    0.13
     aftermath
    0.13
    Activations Density 0.097%

    No Known Activations