© 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. 53932
    Prev
    Next
    INDEX
    Explanations

    film, book, or media titles

    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
     biom
    -0.09
    ussen
    -0.08
    èĽĭçĻ½
    -0.08
    é¡¹çĽ®çļĦ
    -0.08
     boil
    -0.08
    æĶ»æīĵ
    -0.08
    æĿŀ
    -0.08
    åı¯æĢķ
    -0.07
     hardcore
    -0.07
    pants
    -0.07
    POSITIVE LOGITS
    çļĦ人çĶŁ
    0.10
    æ²Ļ滩
    0.10
    è¿Ļéĥ¨çĶµå½±
    0.10
    ä½ķæŶ
    0.10
    ushman
    0.10
    å½±çīĩ
    0.10
    人çĶŁ
    0.09
    çħ¦
    0.09
    ele
    0.09
    åĬ±å¿Ĺ
    0.09
    Activations Density 0.117%

    No Known Activations