© 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. 22222
    Prev
    Next
    INDEX
    Explanations

    probability of letter sequences

    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
    å¾Ĥ
    -0.10
    æĸ°åŁİ
    -0.10
    ç¼Ľ
    -0.09
    ëĭ¤ê°Ģ
    -0.08
    oster
    -0.08
    arn
    -0.08
    orage
    -0.08
    éĺ´éĺ³
    -0.08
    éĿ¡
    -0.08
    æľīä¸Ģ次
    -0.08
    POSITIVE LOGITS
    缶
    0.10
    åIJĥäºı
    0.10
    渲
    0.09
    离
    0.09
    æĪIJé¾Ļ
    0.09
    jee
    0.09
    ä¸įä¼ļæľī
    0.09
    rophe
    0.09
    OTAL
    0.09
    ANJI
    0.09
    Activations Density 0.007%

    No Known Activations