© 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. 11337
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    ä¹ĭ家
    -0.10
    并ä¸įå¤ļ
    -0.09
    éķ¿çº¦
    -0.09
    å¾Īå¥½åľ°
    -0.09
    æŶéĹ´åĴĮ
    -0.08
    à¸Ħà¸ĩ
    -0.08
    ä¸įçĶ±
    -0.08
    ety
    -0.08
    éľ¹
    -0.08
    éķ¿å¾ģ
    -0.08
    POSITIVE LOGITS
    èįŁ
    0.10
    å¸ľ
    0.10
    éĻĦå±ŀ
    0.10
    alus
    0.10
    udden
    0.09
    ogg
    0.09
    æī°
    0.08
    æīĢæīĢ
    0.08
    yntax
    0.08
     ná»ģn
    0.08
    Activations Density 0.022%

    No Known Activations