© 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. 57414
    Prev
    Next
    INDEX
    Explanations

    possessive 's followed by 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
    itics
    -0.10
    ä¸ĢéĹª
    -0.10
    澡
    -0.09
    ä¸įå¿ĺ
    -0.09
    andle
    -0.09
    æĢİä¹Ī说
    -0.09
    è¿Ļè¾¹
    -0.09
    æĪij们éĥ½
    -0.09
    对äºİæĪij们
    -0.09
    éĿ¢ç§¯çº¦
    -0.09
    POSITIVE LOGITS
     been
    0.19
    ed
    0.18
    Been
    0.15
     Been
    0.15
     BEEN
    0.15
     sido
    0.15
    been
    0.14
    åģļè¿ĩ
    0.13
    çľĭè¿ĩ
    0.13
    äºĨ
    0.13
    Activations Density 0.068%

    No Known Activations