© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32733
    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
    绩
    -0.10
     ÙĪØ®
    -0.09
    ñana
    -0.09
    äºĨä¸įå°ij
    -0.08
     McB
    -0.08
    в
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    ENCH
    -0.08
    aku
    -0.08
    formance
    -0.08
    POSITIVE LOGITS
    æİĮéŨ
    0.10
    è¿Ļèά
    0.10
    çģ«çĪĨ
    0.10
    ìł¸
    0.09
    éͲ
    0.09
     обÑĢазом
    0.09
    迷人
    0.08
    å͝
    0.08
    ưu
    0.08
     reps
    0.08
    Activations Density 0.040%

    No Known Activations