© 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. 4162
    Prev
    Next
    INDEX
    Explanations

    DOS and operating systems

    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
    ../../../
    -0.11
    ../
    -0.10
    azor
    -0.09
    秣æĪ¿
    -0.09
    sWith
    -0.09
    èĢĮæĿ¥
    -0.09
    ../../
    -0.08
    ÑĤÑĢа
    -0.08
    itest
    -0.08
    举æĬ¥çĶµè¯Ŀ
    -0.08
    POSITIVE LOGITS
    åĵĩ
    0.10
     ë¶Ī구íķĺê³ł
    0.09
    omething
    0.09
    è§īæĤŁ
    0.08
    éĢĭ
    0.08
    éĥ¨
    0.08
    ierung
    0.08
    Ñĥгл
    0.08
    beck
    0.08
    Invariant
    0.08
    Activations Density 0.038%

    No Known Activations