© 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. 17617
    Prev
    Next
    INDEX
    Explanations

    hypertension, artery, vascular

    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
    èĥİ
    -0.10
    éļĶ
    -0.09
    Subsystem
    -0.09
    大æĸ¹
    -0.09
    .PREFERRED
    -0.09
     Craw
    -0.09
    elic
    -0.08
    .truth
    -0.08
    .AR
    -0.08
    สà¸ĩ
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    ä¸Ģæľ¬
    0.09
    æĹĦ
    0.09
     meth
    0.08
    çī¹æ®Ĭ
    0.08
    ç¡®
    0.08
     Blackburn
    0.08
    管çIJĨåĬŀæ³ķ
    0.08
    æ¶Īè´¹åĵģ
    0.08
    ä½ĵåĪ¶æľºåĪ¶
    0.08
    Activations Density 0.402%

    No Known Activations