© 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. 34322
    Prev
    Next
    INDEX
    Explanations

    film and movie content

    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
    伸
    -0.10
    被æī§è¡Į
    -0.10
    AndWait
    -0.09
    éªĩ
    -0.09
    èĪŁ
    -0.09
    æ¹į
    -0.09
    ä¹ĭä½ľ
    -0.09
    åĪº
    -0.09
    æ°ij主çĶŁæ´»
    -0.09
    usta
    -0.08
    POSITIVE LOGITS
    FTA
    0.11
    æ¥Ń
    0.11
    ä¸ļ
    0.10
     nghiá»ĩp
    0.09
     glamorous
    0.09
    产ä¸ļç»ĵæŀĦ
    0.09
    èģĶ
    0.09
     dance
    0.08
    çĶŁäº§ç»ıèIJ¥
    0.08
    OID
    0.08
    Activations Density 0.112%

    No Known Activations