© 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. 21218
    Prev
    Next
    INDEX
    Explanations

    stay focused, safe, updated, healthy

    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
     Elder
    -0.09
    elder
    -0.09
    how
    -0.09
    orama
    -0.08
    æ¦Ľ
    -0.08
    æĸŃ
    -0.08
    ä¸ĵæłı
    -0.08
    ä¸įçķĻ
    -0.08
    ography
    -0.08
    çļĦåģļæ³ķ
    -0.08
    POSITIVE LOGITS
    èѦæĥķ
    0.09
    SION
    0.09
    è¿ľç¦»
    0.09
    æ¸ħéĨĴ
    0.08
    .GetCurrent
    0.08
    annels
    0.08
     Ñĥзн
    0.08
    éĺĩ
    0.08
    Opens
    0.08
    Iterations
    0.08
    Activations Density 0.016%

    No Known Activations