© 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. 56141
    Prev
    Next
    INDEX
    Explanations

    married people

    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
    ä¸ĩæĪ·
    -0.10
    ç©°
    -0.10
    EMENT
    -0.09
    衲
    -0.09
    é¦į
    -0.09
    楷
    -0.09
     zar
    -0.08
    ĽĦ
    -0.08
     africa
    -0.08
    hana
    -0.08
    POSITIVE LOGITS
    ippo
    0.09
    åĵģ
    0.09
    以åIJİ
    0.09
    æĽ¾åľ¨
    0.09
    åĨľçī§
    0.09
    åĵģç±»
    0.09
    å¿ĥ缮ä¸Ń
    0.08
    ä¸Ģè´¯
    0.08
    /effects
    0.08
    ç§ĺè¯Ģ
    0.08
    Activations Density 0.030%

    No Known Activations