© 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. 57971
    Prev
    Next
    INDEX
    Explanations

    weeks or months or years

    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
    åıł
    -0.12
    ç¾Ĭæ¯Ľ
    -0.09
    äºĮèĥİ
    -0.09
    棺
    -0.09
    è¿Ń
    -0.08
    èµı
    -0.08
     Devin
    -0.08
    åİŁæĿ¥çļĦ
    -0.08
    UDA
    -0.08
    gee
    -0.08
    POSITIVE LOGITS
    ä¸Ģ段æŶéĹ´
    0.15
    å¤ļå¹´çļĦ
    0.14
    两年
    0.14
     years
    0.14
    åĩłå¹´
    0.13
    å¾Īéķ¿æŶéĹ´
    0.12
    è¿Ļ段æŶéĹ´
    0.12
    ä¸īå¹´
    0.12
    åĩłä¸ªæľĪ
    0.12
     months
    0.12
    Activations Density 0.166%

    No Known Activations