© 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. 32924
    Prev
    Next
    INDEX
    Explanations

    BMI and creatinine clearance

    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
    åĬłæĭ¿
    -0.10
    éĻįä½İæĪIJæľ¬
    -0.09
    æīĭå¥Ĺ
    -0.08
    _gene
    -0.08
     ident
    -0.08
     gene
    -0.08
    æĺ¶
    -0.08
    亲æīĭ
    -0.08
    èĦ©
    -0.08
    æį
    -0.08
    POSITIVE LOGITS
    æĪIJ年人
    0.10
    身é«ĺ
    0.10
    alus
    0.10
    BMI
    0.10
    ä½ĵéĩį
    0.10
    æī§ä¸ļ
    0.09
    æ±īåŃIJ
    0.09
     мÑĥжÑĩин
    0.09
     Ñģобой
    0.09
    çĶ·çĶŁ
    0.09
    Activations Density 0.254%

    No Known Activations