© 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. 5638
    Prev
    Next
    INDEX
    Explanations

    ability to act

    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
     pun
    -0.10
    ãģĹãĤĩãģĨ
    -0.09
    ÑĪен
    -0.09
     invol
    -0.09
    æ¶Į
    -0.09
    ãĥĭãĥ¥
    -0.08
     pil
    -0.08
     INV
    -0.08
     VIC
    -0.08
     met
    -0.08
    POSITIVE LOGITS
    é¾Ļæ³ī
    0.09
    çªģå¦Ĥåħ¶æĿ¥
    0.09
    swer
    0.09
    æľīèĥ½åĬĽ
    0.09
    esi
    0.09
    exists
    0.09
    çĶŁäº§èĥ½åĬĽ
    0.09
    åı¼
    0.08
    é¢Ħè§ģ
    0.08
    å¹³å®ī
    0.08
    Activations Density 0.071%

    No Known Activations