© 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. 51795
    Prev
    Next
    INDEX
    Explanations

    infrared optics

    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
    çĥŃæ°´åĻ¨
    -0.09
    (MediaType
    -0.09
    亢
    -0.09
    俺
    -0.08
    äºĨ大éĩıçļĦ
    -0.08
    æĬ¼ãģĹ
    -0.08
     pep
    -0.08
    cpy
    -0.08
    æĻĶ
    -0.08
     aff
    -0.08
    POSITIVE LOGITS
    éĩĩ访æŶ
    0.10
    à¸ļรร
    0.09
    çŃĸ
    0.09
    åĴ«
    0.08
    .Payload
    0.08
    éŀĭ
    0.08
    éĿ´
    0.08
    peak
    0.08
    spm
    0.08
    Charset
    0.08
    Activations Density 0.093%

    No Known Activations