© 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. 39106
    Prev
    Next
    INDEX
    Explanations

    loss, uses, data, behavior

    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
     Leap
    -0.10
    è¢Ĵ
    -0.10
    UNK
    -0.09
    åĩºç¤º
    -0.09
    æĭ¾
    -0.09
    èįĨ
    -0.09
    å¤Ħå¤Ħ
    -0.09
    åħ¬å¼Ģ
    -0.09
    eus
    -0.09
    æĿĤ
    -0.09
    POSITIVE LOGITS
    便åĪ©
    0.08
    æĹħ游æĻ¯åĮº
    0.08
    碣
    0.08
    çĶ±æĸ¼
    0.08
    .getWritableDatabase
    0.08
    丰满
    0.08
    <Any
    0.08
    Animate
    0.08
    åı¯ä»¥æł¹æį®
    0.08
    ä¸Ģé¢Ĺ
    0.08
    Activations Density 0.006%

    No Known Activations