© 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. 48161
    Prev
    Next
    INDEX
    Explanations

    outdoor equipment and activities

    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
    æĪij以为
    -0.10
    天çĦ¶
    -0.10
    æ²Ĩ
    -0.10
    æĪij说
    -0.09
    wald
    -0.09
    ÑĪиÑĢ
    -0.08
     FuÃŁ
    -0.08
    è¿¥
    -0.08
    æĮŁ
    -0.08
    _snd
    -0.08
    POSITIVE LOGITS
    æĶ¯æŁ±
    0.11
    享
    0.09
    åĪĢ
    0.08
    é®
    0.08
    æĸ©
    0.08
    æĿİçĻ½
    0.08
    é²Ī
    0.08
     ty
    0.08
    æįķé±¼
    0.08
    ossip
    0.08
    Activations Density 0.141%

    No Known Activations