© 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. 33706
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by 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
    .INSTANCE
    -0.10
    lein
    -0.09
    å°±å¤ŁäºĨ
    -0.09
    ãģ°ãģĭãĤĬ
    -0.09
    ä¸īåĪĨ
    -0.08
    лоÑĤ
    -0.08
    ãģ¤ãģĦ
    -0.08
    ä¸ĭåİ»
    -0.08
    æĹłä¸į
    -0.08
    NewLabel
    -0.08
    POSITIVE LOGITS
    ä¹Łèĥ½
    0.16
    ä¹Łåı¯
    0.15
    ä¹Łåı¯ä»¥
    0.14
    ä»į
    0.13
    çħ§æł·
    0.13
    ä»įå°Ĩ
    0.13
    åı¦è¡Į
    0.13
     nonetheless
    0.12
    ä»įçĦ¶
    0.12
    ä»įæľī
    0.12
    Activations Density 0.158%

    No Known Activations