© 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. 58543
    Prev
    Next
    INDEX
    Explanations

    most of the

    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
    å¦Ĥä½ķçľĭå¾ħ
    -0.10
    ä¸ĩä¸Ģ
    -0.10
    å¤ļæĸ¹
    -0.08
    èĭ¥å¹²
    -0.08
     certain
    -0.08
    çĿ«
    -0.08
    æŁIJäºĽ
    -0.08
     ×ij×ĵ×Ļ×ķק
    -0.08
    æľīä¸įåIJĮçļĦ
    -0.08
    æĽ´æľī
    -0.08
    POSITIVE LOGITS
    人éĥ½
    0.14
    è¿ĺæĺ¯è¦ģ
    0.13
    éĽĨä¸Ńåľ¨
    0.12
    /all
    0.10
    åī©ä¸ĭ
    0.10
     importantly
    0.10
    åĬĽè¿ĺæĺ¯
    0.10
    owing
    0.09
    åģľçķĻåľ¨
    0.09
    èĥ½å¾ĹåĪ°
    0.09
    Activations Density 0.015%

    No Known Activations