© 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. 48407
    Prev
    Next
    INDEX
    Explanations

    lane width and stretch

    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
    æİ¥åħ¥
    -0.09
    è¾į
    -0.09
    å½¹
    -0.09
    yü
    -0.09
    éķ¿çŁŃ
    -0.09
    asca
    -0.09
    semble
    -0.08
    ç¬ı
    -0.08
     Dip
    -0.08
    è¾ķ
    -0.08
    POSITIVE LOGITS
    容纳
    0.09
    æij¸ç´¢
    0.09
    ipline
    0.09
    _dual
    0.09
    åij¨åĪĬ
    0.08
    ega
    0.08
    æľīæŶ
    0.08
    ç»
    0.08
    OLA
    0.08
    ãĥŀãĤ¤
    0.08
    Activations Density 0.094%

    No Known Activations