© 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. 54313
    Prev
    Next
    INDEX
    Explanations

    blood glucose levels

    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
    etti
    -0.10
    形容
    -0.09
    åıijåŀĭ
    -0.09
    _FETCH
    -0.08
    chester
    -0.08
    icate
    -0.08
    ench
    -0.08
    åıijè¨Ģ
    -0.08
    prt
    -0.08
     Vale
    -0.08
    POSITIVE LOGITS
     levels
    0.12
    levels
    0.11
    _NOW
    0.10
    INGS
    0.10
    ä¸įé«ĺ
    0.10
    ç½ij讯
    0.10
     Levels
    0.09
    çķ¿
    0.09
    æ°´å¹³
    0.09
    åĴĢ
    0.09
    Activations Density 0.067%

    No Known Activations