© 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. 39926
    Prev
    Next
    INDEX
    Explanations

    ISP and service provider

    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
    æ½ĩ
    -0.09
    airo
    -0.09
    åĬ³åĬ¡æ´¾éģ£
    -0.08
    _grp
    -0.08
     onResponse
    -0.08
    è¡·
    -0.08
    家éŨåı£
    -0.08
    æ¸ħé¦Ļ
    -0.08
    é¦Ļèķī
    -0.08
    å¥
    -0.08
    POSITIVE LOGITS
    å¿ĥæĻº
    0.10
    лÑıеÑĤ
    0.09
    æł¹æľ¬
    0.09
    ãģİ
    0.09
    éĻŁ
    0.09
    áĥĴ
    0.09
     parted
    0.09
     ÑĪиÑĢ
    0.09
    踵
    0.09
    acus
    0.09
    Activations Density 0.013%

    No Known Activations