© 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. 21254
    Prev
    Next
    INDEX
    Explanations

    low-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
    è¿ħéĢŁ
    -0.09
    éŃĦ
    -0.08
    çļĦè·Ŀ离
    -0.08
    ä¸ĩåįĥ
    -0.08
    ä¸ĸçķĮä¸ĬæľĢ
    -0.08
    éŁ
    -0.08
    å½ķ
    -0.08
    ä¸ĬçĻ¾
    -0.08
    软
    -0.08
    æ·ĭ
    -0.08
    POSITIVE LOGITS
    -low
    0.13
    enheim
    0.13
    å¾Īä½İ
    0.13
    ä½İ
    0.13
    (low
    0.12
    /high
    0.11
    ä½İåİĭ
    0.11
     (\<
    0.11
    è´±
    0.11
    è¾ĥä½İ
    0.10
    Activations Density 0.147%

    No Known Activations