© 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. 62373
    Prev
    Next
    INDEX
    Explanations

    Chronicles, Adina, myocartitis, antitumor activity

    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
    æĻ°
    -0.10
    bourne
    -0.09
    Scores
    -0.09
     Scores
    -0.09
    bü
    -0.09
    骨干
    -0.08
    tight
    -0.08
    _mA
    -0.08
    ?key
    -0.08
    stamp
    -0.08
    POSITIVE LOGITS
    ä¸Ńæĸ°
    0.09
    æĿIJè´¨
    0.09
    pet
    0.09
    æį»
    0.08
    hort
    0.08
    leck
    0.08
    åIJ¹
    0.08
    æ¬
    0.08
    ä¸ĢæĬ¹
    0.08
    ortex
    0.08
    Activations Density 0.064%

    No Known Activations