© 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. 53946
    Prev
    Next
    INDEX
    Explanations

    filler words and punctuation

    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
    ä¹ħ
    -0.09
    ÙĬض
    -0.09
    æĢĢ念
    -0.09
    温åĴĮ
    -0.09
    å®Ľ
    -0.08
    è¿ĺè®°å¾Ĺ
    -0.08
    å¸Įå°Ķ
    -0.08
    æ²®
    -0.08
    izen
    -0.08
    ä¼ĹçĶŁ
    -0.08
    POSITIVE LOGITS
    åIJĦæľī
    0.09
    ç»ĨèĬĤ
    0.09
    oose
    0.09
    ãĥ©ãĥ³ãĤ¹
    0.09
    æĭ´
    0.08
    -Sep
    0.08
    åĽĽçº§
    0.08
    æł´
    0.08
    åĩºçĤī
    0.08
    è«
    0.08
    Activations Density 0.126%

    No Known Activations