© 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. 55009
    Prev
    Next
    INDEX
    Explanations

    to infinitive 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
    åĻĹ
    -0.10
    åĻĺ
    -0.09
    éŨæĪ·ç½ijç«Ļ
    -0.09
     Gib
    -0.09
    饯
    -0.09
    åIJĮè¡Į
    -0.09
    为主é¢ĺ
    -0.09
    çĿIJ
    -0.09
    æľīä¸įå°ij
    -0.09
    ä¹ĭåĪĿ
    -0.09
    POSITIVE LOGITS
     ÑħоÑĤÑĮ
    0.10
    åĦ
    0.08
    atch
    0.08
    ä¸įæĸŃå®ĮåĸĦ
    0.08
    _transient
    0.07
    æĽ´èĥ½
    0.07
    ãģıãĤĬ
    0.07
    _native
    0.07
    ç§Ģ
    0.07
    èĥ½æĬĬ
    0.07
    Activations Density 0.130%

    No Known Activations