© 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. 50637
    Prev
    Next
    INDEX
    Explanations

    pancreatic cancer

    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
    éĤ¯éĥ¸
    -0.11
    èĥĮä¸Ĭ
    -0.10
    è¹ĩ
    -0.10
    éĵ¨
    -0.09
    ç»ĦåĽ¢
    -0.09
    å¡«è¡¥
    -0.09
    isbury
    -0.09
    大éĻĨ
    -0.09
    åĩij
    -0.09
     HOLDERS
    -0.09
    POSITIVE LOGITS
    èĥ°
    0.11
    lik
    0.09
     pancre
    0.09
    lake
    0.09
     oil
    0.09
    æ²ĥå°Ķ
    0.09
     плоÑħо
    0.09
    éŃģ
    0.08
    æīĵåĩº
    0.08
    äºĭåIJİ
    0.08
    Activations Density 0.230%

    No Known Activations