© 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. 17391
    Prev
    Next
    INDEX
    Explanations

    modal verbs and 'have'/'want'

    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
     zwar
    -0.15
    ä½ĨçĶ±äºİ
    -0.15
    çĦ¶èĢĮ
    -0.15
    åĽºçĦ¶
    -0.14
    ä½Ĩæĺ¯
    -0.14
    èĻ½çĦ¶
    -0.14
     but
    -0.13
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.13
    ä½Ĩæĺ¯åľ¨
    -0.13
    ä½Ĩåľ¨
    -0.13
    POSITIVE LOGITS
    åį´æĺ¯
    0.14
     nevertheless
    0.14
     nonetheless
    0.13
    è¿ĺä¸įæĺ¯
    0.12
    åį»
    0.11
    åı¦æľī
    0.10
    ä¹Łåıªæĺ¯
    0.10
    åIJĮæĹ¶ä¹Ł
    0.10
    ä¹Łèĥ½
    0.10
    并ä¸įæĺ¯
    0.10
    Activations Density 0.767%

    No Known Activations