© 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. 35579
    Prev
    Next
    INDEX
    Explanations

    ciliary dyskinesia

    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
    缦
    -0.10
    æĶ¾ä¸ĭ
    -0.09
    éĶĪ
    -0.09
    æ²®
    -0.09
    åī§æľ¬
    -0.08
    pag
    -0.08
    æİĤ
    -0.08
    ายà¸Ļ
    -0.08
     sol
    -0.08
    èĤ©
    -0.08
    POSITIVE LOGITS
    yne
    0.10
    ATS
    0.09
    ailing
    0.09
    (Adapter
    0.09
    STD
    0.09
    à°³
    0.09
    å¯ĮåIJ«
    0.09
     Dix
    0.09
    cheng
    0.09
    CreateInfo
    0.09
    Activations Density 0.147%

    No Known Activations