© 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. 10007
    Prev
    Next
    INDEX
    Explanations

    backup and disaster recovery

    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
    æĬ¥åºŁ
    -0.09
     sÅĤuż
    -0.09
    æ§Ĭ
    -0.08
    æģ©
    -0.08
    åĨħ马
    -0.08
    æĺ¼å¤ľ
    -0.08
    éĶī
    -0.08
    _GC
    -0.08
    /cpp
    -0.08
    diet
    -0.08
    POSITIVE LOGITS
    å¼Ĥåľ°
    0.13
    çģ¾éļ¾
    0.11
     disaster
    0.09
    禾
    0.09
    éĿĻéĿĻ
    0.09
    æ»ĭåħ»
    0.09
    ä¹¡åľŁ
    0.08
    好èݱåĿŀ
    0.08
    æ¸ħåįİ
    0.08
    succ
    0.08
    Activations Density 0.116%

    No Known Activations