© 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. 27003
    Prev
    Next
    INDEX
    Explanations

    chemotherapy-induced toxicity dysfunction

    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
    ä»İæł¹æľ¬ä¸Ĭ
    -0.08
    okin
    -0.08
    بÙĩ
    -0.08
    ewn
    -0.08
    aign
    -0.08
    ä¹ħ
    -0.08
    à¸Ńà¸ļ
    -0.08
    ¢åįķ
    -0.08
    å½¹
    -0.08
     Samar
    -0.08
    POSITIVE LOGITS
    éĩijéĻµ
    0.09
    åĨ
    0.09
    é¦ĸè½®
    0.09
    ä¸Ģå°ģä¿¡
    0.09
    èĩ§
    0.08
    unread
    0.08
     kap
    0.08
    èĪ±
    0.08
    entin
    0.08
    æ³¾
    0.08
    Activations Density 0.342%

    No Known Activations