© 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. 38479
    Prev
    Next
    INDEX
    Explanations

    help you or others

    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
    ucker
    -0.10
    éĤĪ
    -0.09
    对ä»ĸ们
    -0.09
     Dix
    -0.09
    磼
    -0.09
    incer
    -0.08
    ç¯ĩ
    -0.08
    icot
    -0.08
    åĨħçļĦ
    -0.08
    åľ¨åIJĮä¸Ģ
    -0.08
    POSITIVE LOGITS
    elon
    0.09
    éĻ¤æѤ
    0.09
    åĮĸåIJĪçī©
    0.09
    å´ĸ
    0.08
    deg
    0.08
    æ·Į
    0.08
    åIJĮæĹ¶ä¹Ł
    0.08
     Hus
    0.08
    éģµ
    0.08
    lessly
    0.08
    Activations Density 0.027%

    No Known Activations