© 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. 54985
    Prev
    Next
    INDEX
    Explanations

    money raised or support

    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
    æ¯ķç«Łæĺ¯
    -0.10
    bourne
    -0.08
     Succ
    -0.08
     kỳ
    -0.08
    ãģ¾ãģķ
    -0.08
    _BG
    -0.08
    å´®
    -0.08
     tats
    -0.08
    DOM
    -0.08
    é«Ķé©Ĺ
    -0.08
    POSITIVE LOGITS
    è¶ħè¿ĩäºĨ
    0.13
    è¶ħé¢Ŀ
    0.11
    è¶ħåĩº
    0.11
    款项
    0.11
    缸åĬ©
    0.10
    è¾¾åĪ°äºĨ
    0.10
    è¶ħè¿ĩ
    0.10
    åıĸå¾ĹäºĨ
    0.10
    åĭŁéĽĨ
    0.10
    ä¸įå¿į
    0.09
    Activations Density 0.039%

    No Known Activations