© 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. 48582
    Prev
    Next
    INDEX
    Explanations

    hot air and wind

    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
    èĺħ
    -0.11
    åºľ
    -0.10
    halt
    -0.10
    笼
    -0.09
    éĥİ
    -0.09
    è´¹çİĩ
    -0.09
    çŃĩ
    -0.09
    çİĭåºľ
    -0.09
    æ£Ģ
    -0.09
    acements
    -0.09
    POSITIVE LOGITS
     sweeping
    0.09
    éŁ³
    0.09
    .TryParse
    0.09
    8
    0.09
    é«ĺåĩº
    0.08
    anders
    0.08
    IPA
    0.08
    æī«ä¸Ģ
    0.08
    9
    0.08
    rit
    0.08
    Activations Density 0.044%

    No Known Activations