© 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. 31873
    Prev
    Next
    INDEX
    Explanations

    ers adding suffixes

    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
    èĬľ
    -0.09
    çī¹åĪ«æĺ¯åľ¨
    -0.09
    æł¸å¿ĥæĬĢæľ¯
    -0.08
    æĦı大
    -0.08
    vida
    -0.08
    سÙģ
    -0.08
    á»įng
    -0.08
    aysia
    -0.08
    ä¼¼çļĦ
    -0.08
    çļĦèĥĮåIJİ
    -0.08
    POSITIVE LOGITS
    ers
    0.30
    èĢħçļĦ
    0.27
    èĢħ
    0.25
    er
    0.22
    åĻ¨
    0.21
    åijĺ
    0.21
    èĢħãģ®
    0.20
    èĢħãģ¯
    0.19
    èĢħãģĮ
    0.19
    åĵ¡
    0.18
    Activations Density 0.679%

    No Known Activations