© 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. 53128
    Prev
    Next
    INDEX
    Explanations

    taxonomy and classification

    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
    éĩįä¸Ń
    -0.11
    éĢŀ
    -0.10
    骢
    -0.10
    å½ĵåľ°æŶéĹ´
    -0.09
    çĿĢä»ĸ
    -0.09
    æµ·å¤ĸå¸Ĥåľº
    -0.09
    åĬ©
    -0.09
    鸳
    -0.09
    amus
    -0.09
    çĪ½
    -0.09
    POSITIVE LOGITS
    å°Ħ
    0.09
    iscal
    0.09
    èį·
    0.08
    èĥĮæĻ¯
    0.08
    o
    0.08
    åĬłä¹ĭ
    0.08
    Streamer
    0.08
    tog
    0.08
    /categories
    0.07
    çļĩ家
    0.07
    Activations Density 0.098%

    No Known Activations