© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    liver disease and protein

    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
    ingly
    -0.10
    éĹŃ
    -0.09
    è°ģçŁ¥éģĵ
    -0.09
    PageIndex
    -0.09
    adier
    -0.09
    媾
    -0.09
     ìŀħ
    -0.08
    踵
    -0.08
    UR
    -0.08
    åıįå¤į
    -0.08
    POSITIVE LOGITS
    åĭĩäºİ
    0.10
     Stap
    0.09
    odule
    0.09
    æ¹¾
    0.09
    åľ©
    0.08
    ieren
    0.08
     Leone
    0.08
    fly
    0.08
    _dll
    0.08
    åijĬ
    0.08
    Activations Density 0.117%

    No Known Activations