© 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. 31259
    Prev
    Next
    INDEX
    Explanations

    breeding and breeds

    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
     Schmidt
    -0.09
     undue
    -0.09
    owers
    -0.09
    aland
    -0.09
     pil
    -0.08
    ï¾ŀ
    -0.08
    èĥ¶åĽĬ
    -0.08
    ion
    -0.08
    æİ¥è¿ĩ
    -0.08
    é»İæĺİ
    -0.08
    POSITIVE LOGITS
    婦
    0.10
    æªĶ
    0.09
    åĿŀ
    0.09
    ÑĥÑī
    0.09
    iate
    0.09
    iosity
    0.09
    ings
    0.09
    haven
    0.09
    zel
    0.09
    æľīæľŁ
    0.09
    Activations Density 0.020%

    No Known Activations