© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37517
    Prev
    Next
    INDEX
    Explanations

    ensuing explanation or study

    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
    çľ¼ä¸ĭ
    -0.10
    çİ°éĺ¶æ®µ
    -0.10
    å³Ń
    -0.09
    èĤļ
    -0.09
    lags
    -0.09
    èĬ¯çīĩ
    -0.09
    æīİ
    -0.09
     lingering
    -0.09
    DRAW
    -0.08
    ноÑģÑĤÑĮÑİ
    -0.08
    POSITIVE LOGITS
    æİ¥ä¸ĭæĿ¥
    0.10
    éļıä¹ĭ
    0.09
    ä¸Ģç³»åĪĹ
    0.09
    rey
    0.09
     dara
    0.09
    unik
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
    åİ¥
    0.09
    UDO
    0.08
    eway
    0.08
    Activations Density 0.035%

    No Known Activations