© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8557
    Prev
    Next
    INDEX
    Explanations

    fatty acids and radicals

    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
    аÑĨион
    -0.09
    æĿĤçī©
    -0.09
    åłª
    -0.09
    亲åıĭ
    -0.09
    alice
    -0.09
    favicon
    -0.09
    aint
    -0.09
    ç¥ļ
    -0.09
    ãĤĪãģĨãģ§
    -0.08
    éĻĦåĬł
    -0.08
    POSITIVE LOGITS
    们çļĦ
    0.11
    们
    0.11
    emia
    0.10
    èĪ«
    0.09
    åĢij
    0.09
    istani
    0.09
    ами
    0.09
    å°ıåŃIJ
    0.08
    å¸Į
    0.08
    usal
    0.08
    Activations Density 0.309%

    No Known Activations