© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36941
    Prev
    Next
    INDEX
    Explanations

    Rush or Kiss

    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
    çľĭçĤ¹
    -0.11
    级åĪ«çļĦ
    -0.09
    åĽ½èµĦ
    -0.09
    èĮĥåĽ´åĨħ
    -0.09
    ucchini
    -0.09
    иÑħ
    -0.08
    æµģ产
    -0.08
    æݺ
    -0.08
    ä¸Ģæŀ¶
    -0.08
    uard
    -0.08
    POSITIVE LOGITS
    -encoded
    0.09
    éľĨ
    0.08
     getActivity
    0.08
    лов
    0.08
    å½ķåıĸ
    0.08
    å²ij
    0.08
    è§Ħå¾ĭ
    0.08
     sä
    0.08
    stalk
    0.08
    kol
    0.07
    Activations Density 0.002%

    No Known Activations