© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6714
    Prev
    Next
    INDEX
    Explanations

    graduated from university or school

    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
    çī¹æ´¾åijĺ
    -0.09
    enstein
    -0.08
     excerpt
    -0.08
    ablish
    -0.08
    abee
    -0.07
    aggio
    -0.07
     graceful
    -0.07
    å¥ijæľº
    -0.07
    广éĺĶ
    -0.07
    Ãłi
    -0.07
    POSITIVE LOGITS
    æľĢå¿«çļĦ
    0.12
    é»İ
    0.09
    xin
    0.09
    大åѦæ¯ķä¸ļ
    0.09
    AutoSize
    0.09
    ãģ¨ãģ¯ãģĦ
    0.08
    üt
    0.08
    ç
    0.08
    APA
    0.08
    ä½Ĩæĺ¯å¯¹äºİ
    0.08
    Activations Density 0.030%

    No Known Activations