© 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. 61027
    Prev
    Next
    INDEX
    Explanations

    obtain license

    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
    俾
    -0.09
    arin
    -0.08
     heavily
    -0.07
    prior
    -0.07
    ä¼ĺåħĪ
    -0.07
     suff
    -0.07
    èģĶåIJĪä¼ļ
    -0.07
     Suff
    -0.07
    çijŁ
    -0.07
    udi
    -0.07
    POSITIVE LOGITS
    ฤ
    0.11
    æĮ«æĬĺ
    0.10
    å¸ı
    0.10
    è´´è¿ij
    0.10
    足迹
    0.10
    度è¿ĩ
    0.10
    ç»ļ丽
    0.09
    ->$
    0.09
    å±Ī
    0.09
     акÑĤÑĥ
    0.09
    Activations Density 0.027%

    No Known Activations