© 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. 19157
    Prev
    Next
    INDEX
    Explanations

    could do

    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
    æľīä¸Ģ次
    -0.08
    è¡«
    -0.08
    åĢĶ
    -0.08
    à¹ģà¸Ľà¸¥
    -0.08
    éĿŀ常éĩįè¦ģ
    -0.08
    尤为éĩįè¦ģ
    -0.07
    [âĢ¦]
    -0.07
    èµĽåŃ£
    -0.07
    ModifiedDate
    -0.07
    被æĬĵ
    -0.07
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.10
    ä¸Ģ缴
    0.10
    ä½ĨæĪij们
    0.10
    åĮ¡
    0.09
    ä¸Ĭä¸ĭ
    0.09
     нап
    0.09
    éĻ°
    0.09
    agna
    0.09
    olin
    0.09
    åѤ
    0.09
    Activations Density 0.204%

    No Known Activations