© 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. 31041
    Prev
    Next
    INDEX
    Explanations

    done for you

    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
    биÑĤ
    -0.09
    åģĩè£ħ
    -0.09
    .fake
    -0.09
    ãĤ¹ãĥĿ
    -0.09
    æĸ°åĮº
    -0.08
    uce
    -0.08
     babes
    -0.08
    rell
    -0.08
    åĽļ
    -0.08
    éĺ¶æ®µæĢ§
    -0.08
    POSITIVE LOGITS
    æĤĦæĤĦ
    0.09
    _rs
    0.09
    ç»ĻåŃ©åŃIJ
    0.08
    修订
    0.08
    å¼Ģåı£
    0.08
    ustr
    0.08
    åĬ¨çĶŁæĪIJ
    0.08
    éĩijåŃĹå¡Ķ
    0.08
    åħĪæĺ¯
    0.08
    oga
    0.08
    Activations Density 0.045%

    No Known Activations