© 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. 39591
    Prev
    Next
    INDEX
    Explanations

    're doing

    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
    hn
    -0.08
    æīĢåľ¨çļĦ
    -0.07
     Ùħجرد
    -0.07
    æķ°çĽ®
    -0.07
    èĨĿ
    -0.07
    çľ¨çľ¼
    -0.07
    è¿Ļæīį
    -0.07
    	fire
    -0.07
    uper
    -0.07
    ét
    -0.07
    POSITIVE LOGITS
    夸大
    0.11
    åıijæĮ¥ä½ľçĶ¨
    0.10
    è¿Ļ个éĹ®é¢ĺ
    0.09
    atl
    0.09
    dek
    0.09
    éģĺ
    0.09
    çŃĸ
    0.09
    rud
    0.09
    溽
    0.09
    ASF
    0.09
    Activations Density 0.034%

    No Known Activations