© 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. 57227
    Prev
    Next
    INDEX
    Explanations

    pronoun + modal verb

    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
    jem
    -0.09
    ampo
    -0.09
    被认为
    -0.09
    ä¸įäºĨ
    -0.08
    -tab
    -0.08
    ä¸Ģå°ģ
    -0.08
    å°±è¿ij
    -0.08
    sis
    -0.08
    achi
    -0.08
     Bren
    -0.08
    POSITIVE LOGITS
    åºĶ该å¦Ĥä½ķ
    0.10
    äºı
    0.10
    æľīå¿ħè¦ģ
    0.09
    æľªæĿ¥
    0.09
    ught
    0.09
    åĨįä¹Ł
    0.09
    åľ¨æľªæĿ¥
    0.09
    åºĶ该
    0.09
     needing
    0.09
    è¿ĺéľĢè¦ģ
    0.08
    Activations Density 0.076%

    No Known Activations