© 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. 49617
    Prev
    Next
    INDEX
    Explanations

    detective/crime fiction series

    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
    ç¥Ŀç¦ı
    -0.09
    ä¼łæŁĵ
    -0.08
     squirt
    -0.08
    -valid
    -0.08
    EPS
    -0.08
    cem
    -0.08
    æİ°
    -0.08
    åĶ±
    -0.08
    éļ¾æ°ij
    -0.08
    æİı
    -0.08
    POSITIVE LOGITS
    侦
    0.15
    åĬŀæ¡Ī
    0.15
    åĪij侦
    0.15
    çĬ¯ç½ª
    0.14
     crime
    0.14
    侦æİ¢
    0.13
    crime
    0.13
    ä¾¦æŁ¥
    0.13
     detective
    0.13
    æݨçIJĨ
    0.13
    Activations Density 0.087%

    No Known Activations