© 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. 34646
    Prev
    Next
    INDEX
    Explanations

    starts sentence with question mark

    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
    æ¦Ħ
    -0.10
    ç¬ĶèĢħ
    -0.09
    æĮĩ令
    -0.09
    çĤ³
    -0.09
    æŃ¤äºº
    -0.08
    ÙģÙĦ
    -0.08
    èŃ¦ç¤º
    -0.08
     пÑĢид
    -0.08
    æĮ¥æīĭ
    -0.08
    /wiki
    -0.08
    POSITIVE LOGITS
    ç§ĺè¯Ģ
    0.11
    à¸ķà¸Ńà¸ļ
    0.10
    obre
    0.10
    è§īå¾Ĺå¾Ī
    0.10
    çŃĶ
    0.10
    æĪij认为
    0.09
    è°ĪåıĬ
    0.09
    å¦Ĥä½ķçľĭå¾ħ
    0.09
    æľĢåĸľæ¬¢
    0.09
    Asked
    0.09
    Activations Density 0.070%

    No Known Activations