© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10340
    Prev
    Next
    INDEX
    Explanations

    lords, chiefs, monarchs, barons

    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
     stiff
    -0.09
     vess
    -0.09
    amm
    -0.09
    èĻ±
    -0.09
    çĶ¬
    -0.09
    åħµåĻ¨
    -0.08
    åIJĮè¡Į
    -0.08
    éĻ¡
    -0.08
     vá»ijn
    -0.08
    éŁŃ
    -0.08
    POSITIVE LOGITS
    é¦ĸé¢Ĩ
    0.10
    äºī夺
    0.10
    cer
    0.09
    驼
    0.09
    å¤ĸåªĴ
    0.09
    æĵį纵
    0.09
    åŀĦæĸŃ
    0.09
    éĹ
    0.09
    大æĪ·
    0.08
    лаÑģÑĤ
    0.08
    Activations Density 0.119%

    No Known Activations