© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19056
    Prev
    Next
    INDEX
    Explanations

    brand name, reputation, prestige

    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
    çļĦçģµéŃĤ
    -0.09
    å¤Ń
    -0.09
    å¾ĹæĦı
    -0.09
    æk
    -0.09
    è¯Ħ为
    -0.08
     далÑĮ
    -0.08
    çģµéŃĤ
    -0.08
     COMPLETE
    -0.08
    æĺ¼å¤ľ
    -0.08
    urer
    -0.08
    POSITIVE LOGITS
    åħīçݯ
    0.13
    éĩijåŃĹ
    0.12
    带åĬ¨
    0.12
    åĬłæĮģ
    0.10
    家åĸ»æĪ·æĻĵ
    0.10
    اÙĬ
    0.10
    æ¯ĭ
    0.10
    ault
    0.09
    åIJįæł¡
    0.09
    éĻ¡
    0.09
    Activations Density 0.208%

    No Known Activations