© 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. 21147
    Prev
    Next
    INDEX
    Explanations

    family relationships and successors

    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
    èĢĮåĩº
    -0.09
    ÙĤØ©
    -0.09
    éĹ°
    -0.09
    åĭ¤
    -0.09
    éľĨ
    -0.08
    ID
    -0.08
     PAD
    -0.08
     defect
    -0.08
    wal
    -0.08
    夫人
    -0.08
    POSITIVE LOGITS
    ä»
    0.10
    佬
    0.10
    æķ£çĥŃ
    0.09
    åķ¤éħĴ
    0.09
    _stride
    0.09
    abox
    0.09
    stras
    0.09
    Jur
    0.09
    èĭ¥å¹²
    0.09
    飯
    0.09
    Activations Density 0.002%

    No Known Activations