© 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. 56769
    Prev
    Next
    INDEX
    Explanations

    cost or benefit

    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
    梵
    -0.10
    糧
    -0.10
    çıī
    -0.09
    rome
    -0.09
     Cong
    -0.08
    INDER
    -0.08
    çŃĿ
    -0.08
    ê³Ħ
    -0.08
    зна
    -0.08
     Alv
    -0.08
    POSITIVE LOGITS
    åĽŀæĬ¥
    0.13
    åıĹçĽĬ
    0.11
    åĪĴç®Ĺ
    0.11
    æĶ¶åĽŀ
    0.11
    åĽŀæĶ¶
    0.10
     ROI
    0.09
    1
    0.09
    è¡¥åģ¿
    0.09
    æĬµ
    0.09
    èİ·åĪ©
    0.09
    Activations Density 0.037%

    No Known Activations