© 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. 53423
    Prev
    Next
    INDEX
    Explanations

    all used

    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
    æĥ³èµ·æĿ¥
    -0.09
    æĪijåıªæĺ¯
    -0.09
    èĢĮåİ»
    -0.08
    æ½®æµģ
    -0.08
    ä¹Łåıªæľī
    -0.08
    -regexp
    -0.08
    /fire
    -0.08
    åĪ«è¯´
    -0.08
    æŃ£åĽłä¸º
    -0.08
     ÑģÑĭÑĢ
    -0.08
    POSITIVE LOGITS
    åĪ¤
    0.10
    é©Ń
    0.09
    thon
    0.09
    voice
    0.09
    ways
    0.09
    èµIJ
    0.09
    泯
    0.09
    è¿Ľåħ¥åĪ°
    0.08
    ideo
    0.08
     Durant
    0.08
    Activations Density 0.018%

    No Known Activations