© 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. 57238
    Prev
    Next
    INDEX
    Explanations

    Halloween and pumpkin related terms

    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
    åĬłå¤§å¯¹
    -0.11
    带ä¸Ĭ
    -0.11
    nia
    -0.09
     Baths
    -0.09
    群éĩĮ
    -0.09
    èĪĮ
    -0.09
     palms
    -0.09
    auge
    -0.09
    æ»ļåĬ¨
    -0.09
    ç¾½
    -0.09
    POSITIVE LOGITS
     Halloween
    0.13
     pumpkin
    0.10
    åĩĮ
    0.10
    ðŁİĥ
    0.09
    out
    0.09
    _DIRECTORY
    0.09
    rek
    0.09
    æ°Ķæģ¯
    0.08
     Pumpkin
    0.08
    ç¥Ń
    0.08
    Activations Density 0.110%

    No Known Activations