© 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. 5076
    Prev
    Next
    INDEX
    Explanations

    numbers followed by dates or league names

    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
    acco
    -0.10
    å½±ä¸ļ
    -0.10
    èĻ¹
    -0.10
    åĵĹ
    -0.10
    essed
    -0.09
    åĪ¥ãģ®
    -0.09
    æIJľæķij
    -0.09
    æ¸į
    -0.09
    éĺĢéŨ
    -0.09
    -await
    -0.09
    POSITIVE LOGITS
    ãģ©ãģĵãĤį
    0.10
     runtime
    0.08
    hardt
    0.08
    ç¥Ī祷
    0.07
    orns
    0.07
    å¼Ģå±Ģ
    0.07
    çŁ¥éģĵèĩªå·±
    0.07
    ä¸Ńåľº
    0.07
    åĬ¨æĦŁ
    0.07
    空éĹ´
    0.07
    Activations Density 0.138%

    No Known Activations