© 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. 32638
    Prev
    Next
    INDEX
    Explanations

    at [university name]

    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
    æŃĩ
    -0.10
    éļĶ
    -0.09
    æĬ¼
    -0.09
     Lomb
    -0.08
     Ventura
    -0.08
    IGO
    -0.08
    æĸ©
    -0.08
    çĭ
    -0.08
    æĬĺ
    -0.08
    ldata
    -0.08
    POSITIVE LOGITS
    /tiny
    0.10
    å¿ĺè®°äºĨ
    0.09
    ä¾
    0.09
    å³¥
    0.09
    éĻ¢æł¡
    0.09
    ä¹ĭ声
    0.09
    ç½Ħ
    0.09
    å¤ļä¹Ī
    0.08
    ä»İæĿ¥æ²¡æľī
    0.08
    ÑģÑĤавлен
    0.08
    Activations Density 0.044%

    No Known Activations