© 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. 48231
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    è¿Ļ家åħ¬åı¸
    -0.09
    ä¸ĵ线
    -0.09
    åĮ£
    -0.09
    æŀ¢
    -0.09
    éĬ®
    -0.08
    è¿ĶåĽŀæIJľçĭIJ
    -0.08
    //=
    -0.08
    æļ
    -0.08
     trivial
    -0.08
    åħħåĪĨä½ĵçİ°
    -0.08
    POSITIVE LOGITS
    pré
    0.09
    æĬij
    0.09
    âĢº
    0.08
    Anyway
    0.08
    Convertible
    0.08
    çĥĿ
    0.08
    å¤Ħç½®
    0.08
    ä¹Łä¸įæķ¢
    0.08
     обÑĭ
    0.08
    ovation
    0.08
    Activations Density 0.434%

    No Known Activations