© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    question mark followed by word

    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
    avern
    -0.10
    客æĪ·æľįåĬ¡
    -0.09
    好äºĭ
    -0.09
    åħ®
    -0.09
    欣æħ°
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.09
    _FWD
    -0.09
    桧
    -0.09
     ÑģÑĦ
    -0.09
    æ³Ĺ
    -0.09
    POSITIVE LOGITS
     Provision
    0.09
    æĶ¥
    0.09
    تاÙĨ
    0.08
    æł¹æľ¬ä¸į
    0.08
    ective
    0.08
    庾
    0.08
    eting
    0.08
    ir
    0.08
    游ä¹IJ
    0.08
    ç»ĵ论
    0.08
    Activations Density 0.027%

    No Known Activations