© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8470
    Prev
    Next
    INDEX
    Explanations

    than or except

    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
    æĪª
    -0.09
    çĸĨ
    -0.08
    ogen
    -0.08
    æĶĴ
    -0.08
    Îŀ
    -0.08
    bum
    -0.08
    éĿ
    -0.08
    è¿Ļå°±
    -0.08
     zwar
    -0.08
    éĢı
    -0.08
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.11
    æĦıä¹īä¸ĬçļĦ
    0.10
    亹
    0.09
    继ç»Ń
    0.09
    èĩ´åĬĽ
    0.08
    zilla
    0.08
    å®ĥæĺ¯
    0.08
    ÑĤик
    0.08
    ä¹Łä¸įæĥ³
    0.08
    alph
    0.08
    Activations Density 0.039%

    No Known Activations