© 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. 32083
    Prev
    Next
    INDEX
    Explanations

    save time or money

    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
     Moff
    -0.09
    ave
    -0.08
    èģĬ
    -0.08
    è¦ģæĥ³
    -0.08
    aro
    -0.08
    uda
    -0.08
    åŀļ
    -0.08
    èģªæĺİ
    -0.08
    æĮīä¸ĭ
    -0.08
    alk
    -0.08
    POSITIVE LOGITS
    äºĨä¸įå°ij
    0.10
    ÙĬÙĪÙħ
    0.10
    wit
    0.10
     Ñģобой
    0.10
    æŶéĹ´åĴĮ
    0.09
    ispers
    0.09
    unei
    0.09
    éĮ¢
    0.09
    è¦ĭãģŁ
    0.09
    exion
    0.09
    Activations Density 0.012%

    No Known Activations