© 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. 16938
    Prev
    Next
    INDEX
    Explanations

    metabolic syndrome

    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
    _sites
    -0.10
    æĿ¿æĿIJ
    -0.10
    æĬ±
    -0.09
    edelta
    -0.09
    è·ŁæĪij
    -0.09
    æĸ°æĬĢæľ¯
    -0.09
    åĩ«
    -0.09
    èį¦
    -0.09
    è·Łå¥¹
    -0.09
    orde
    -0.08
    POSITIVE LOGITS
    åī¥ç¦»
    0.09
    éĺ²èĮĥ
    0.08
    漩
    0.08
    åĩĨ
    0.08
    plode
    0.08
    ترا
    0.08
    åħĢ
    0.08
    Facade
    0.08
    èľļ
    0.08
    Glass
    0.08
    Activations Density 0.180%

    No Known Activations