© 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. 10720
    Prev
    Next
    INDEX
    Explanations

    holiday destinations and activities

    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
     usually
    -0.09
    ä¸įåĪ°
    -0.08
    åĩłä¹İ
    -0.08
    èIJ¼
    -0.08
    å¢ħ
    -0.08
    ä½łæĺ¯
    -0.08
    éļıæīĭ
    -0.08
    quate
    -0.08
    ä½łèĩªå·±
    -0.08
    éĩįè¦ģä½ľçĶ¨
    -0.08
    POSITIVE LOGITS
    æĺİå¹´
    0.15
    尽快
    0.15
    å±ĬæŶ
    0.14
    åĪ°æŶåĢĻ
    0.13
    ä¸ĭåij¨
    0.13
    å°ĨæĿ¥
    0.13
    åģļä¸ĢäºĽ
    0.12
    å°½åı¯èĥ½
    0.12
     someday
    0.12
    äºīåıĸ
    0.12
    Activations Density 0.181%

    No Known Activations