© 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. 7793
    Prev
    Next
    INDEX
    Explanations

    options for temperature or level

    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
    _CM
    -0.09
    éĶŁ
    -0.09
    仿
    -0.08
    èŀ³
    -0.08
    .rf
    -0.08
    داع
    -0.08
    ä»ĺ
    -0.08
    TED
    -0.08
    VML
    -0.08
    æ¸ħéĨĴ
    -0.08
    POSITIVE LOGITS
    ä¸IJ
    0.10
    ä¸ĭæ²ī
    0.09
    大å¦Ī
    0.08
    å°ıèħ¿
    0.08
    讨
    0.08
    è¿ĩåĪĨ
    0.08
    åİ¿åŁŁ
    0.08
    åĭ¾
    0.08
    partment
    0.08
    cca
    0.08
    Activations Density 0.034%

    No Known Activations