© 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. 37577
    Prev
    Next
    INDEX
    Explanations

    amazon.com other parties

    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
    庶
    -0.09
    æķ´ä¸ªäºº
    -0.09
    esta
    -0.09
    èIJ½åľ¨
    -0.09
    eli
    -0.08
    oud
    -0.08
    æŃ£ç¡®çļĦ
    -0.08
    对çŃĸ
    -0.08
    ç²Ĵ
    -0.08
    åħīè¾ī
    -0.08
    POSITIVE LOGITS
    ç´«
    0.11
    æ¯Ĺ
    0.09
    èĦĨ
    0.09
    .acquire
    0.09
    west
    0.08
    ä»İæľª
    0.08
    ovich
    0.08
    天é¹ħ
    0.08
    udder
    0.08
    éĢıéľ²
    0.08
    Activations Density 0.009%

    No Known Activations