© 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. 32128
    Prev
    Next
    INDEX
    Explanations

    Cherokee, aturational, initio, Copyright, abstract

    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¸ĢåŃĹ
    -0.10
    ichel
    -0.09
    欹
    -0.09
    åĢĴ
    -0.09
    à¤ŀ
    -0.09
    è¿·æĥij
    -0.08
    æĿµ
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    åij½
    -0.08
    amient
    -0.08
    POSITIVE LOGITS
    æľ¬ç«Ļ
    0.10
     majority
    0.10
    å¤ĸæı´
    0.09
    御
    0.08
    ught
    0.08
    æ¡ĥ
    0.08
    ãĥĥ
    0.08
    éĥ½æľīèĩªå·±
    0.08
     Won
    0.08
     Hend
    0.08
    Activations Density 0.158%

    No Known Activations