© 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. 26688
    Prev
    Next
    INDEX
    Explanations

    instructions to proceed

    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
    åħ¶ä¸ŃåĮħæĭ¬
    -0.10
    稿件
    -0.09
     possibly
    -0.09
    æ¸ħ代
    -0.08
    åĬĿ
    -0.08
    å¸ĮæľĽå¤§å®¶
    -0.08
    å½¼
    -0.08
    åŃĶ
    -0.08
    eña
    -0.08
    对ä»ĺ
    -0.08
    POSITIVE LOGITS
     simply
    0.11
    å¾Īç®Ģåįķ
    0.09
    åıªéľĢè¦ģ
    0.09
    åıªéľĢ
    0.09
    msp
    0.09
    äºĭåħĪ
    0.09
    ä¸Ģæĸ¹
    0.09
    秧
    0.08
    åľ¨ç½ij绾
    0.08
     simplement
    0.08
    Activations Density 0.041%

    No Known Activations