© 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. 33594
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their treatments

    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¸ĸéĹ´
    -0.09
    缪
    -0.09
    çĻ½çĻ½
    -0.09
    æľįåĬ¡è´¨éĩı
    -0.08
     Rush
    -0.08
    å¾Ī容æĺĵ
    -0.08
    åºĶæľīçļĦ
    -0.08
    _FA
    -0.08
    çĬ´
    -0.08
    çģ«èĬ±
    -0.08
    POSITIVE LOGITS
    å·²ç»ıæľī
    0.09
    屡
    0.09
    (Target
    0.09
    ARGET
    0.09
    æģ¶
    0.09
    /downloads
    0.09
    æĿ¡è¯Ħ论
    0.09
    次è¦ģ
    0.08
    =target
    0.08
    targets
    0.08
    Activations Density 0.701%

    No Known Activations