© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38095
    Prev
    Next
    INDEX
    Explanations

    NATO allies and actions

    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
    å®ĵ
    -0.09
    å²Ľä¸Ĭ
    -0.09
    çľĭä»ĸ
    -0.09
    AndGet
    -0.09
    Margins
    -0.08
    ments
    -0.08
    SETS
    -0.08
    avor
    -0.08
    ipher
    -0.08
    åĩĢèµĦ产
    -0.08
    POSITIVE LOGITS
    ç§ĺ书éķ¿
    0.09
    æĹĹä¸ĭçļĦ
    0.09
    æľĭåıĭ
    0.09
    æ±Ĺ
    0.08
    罩
    0.08
    æ£ĺ
    0.08
     hät
    0.08
    æ¶İ
    0.08
    岸
    0.08
    æĹĹä¸ĭ
    0.08
    Activations Density 0.006%

    No Known Activations