© 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. 5197
    Prev
    Next
    INDEX
    Explanations

    instruction verbs

    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
    åĩĨå¤ĩå·¥ä½ľ
    -0.09
    éĩįè¦ģåİŁåĽł
    -0.09
    åŁł
    -0.09
    ضا
    -0.09
     mcc
    -0.08
    举åĬ¨
    -0.08
    çķĢ
    -0.08
    çļĦä¸Ģ大
    -0.08
    ãģĭãģªãĤĬ
    -0.08
    为ä»Ģä¹Īè¦ģ
    -0.08
    POSITIVE LOGITS
     yourself
    0.12
    ä¸įè¦ģ
    0.10
     Yourself
    0.10
    /Create
    0.10
    ä¸įè¦ģåĨį
    0.10
    ä½łèĩªå·±
    0.09
    æĶ¯æĮģ
    0.08
     تش
    0.08
    ipro
    0.08
    çľĭçľĭ
    0.08
    Activations Density 0.049%

    No Known Activations