© 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. 21171
    Prev
    Next
    INDEX
    Explanations

    might followed by verbs

    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
    itti
    -0.09
    StatusCode
    -0.09
    OMEM
    -0.09
    ssel
    -0.09
    lov
    -0.09
    AXB
    -0.08
    oden
    -0.08
    ä¸įæĢķ
    -0.08
     Aval
    -0.08
     Owens
    -0.08
    POSITIVE LOGITS
    说æĺ¯
    0.10
    æĺ¯æľĢ好çļĦ
    0.09
    è§ı
    0.09
    çľ¼åīįçļĦ
    0.09
    è¸ıåħ¥
    0.09
    ÙĬÙĪÙĨ
    0.09
    æī¼
    0.08
    è·Łä¸įä¸Ĭ
    0.08
    ulers
    0.08
    ä¿Ŀåħ»
    0.08
    Activations Density 0.038%

    No Known Activations