© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23328
    Prev
    Next
    INDEX
    Explanations

    box office hits and bombs

    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
    ç²īèī²
    -0.10
    inka
    -0.10
    æ£ķèī²
    -0.09
    å²ĺ
    -0.09
    ä¼ļä¼ļéķ¿
    -0.09
    Pink
    -0.09
    æªĶ
    -0.09
    /op
    -0.08
    ãģªãģı
    -0.08
     Ferd
    -0.08
    POSITIVE LOGITS
    åij½ä¸Ń
    0.10
    èĩªå¾ĭ
    0.09
     Gül
    0.09
    sav
    0.09
    á»ĩ
    0.09
     sidel
    0.08
    æ¯ĵ
    0.08
    ÑĨион
    0.08
    ÙĬست
    0.08
    (Temp
    0.08
    Activations Density 0.006%

    No Known Activations