© 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. 55512
    Prev
    Next
    INDEX
    Explanations

    imperative verbs followed by "me", "yourself", or "it"

    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
    æ°¸åĪ©
    -0.11
    大åıij
    -0.09
    Persons
    -0.09
    ialias
    -0.08
    (:,:,
    -0.08
    ä»Ŀ
    -0.08
    磼
    -0.08
    empor
    -0.08
    ,nil
    -0.08
    éĶ¦ç»£
    -0.08
    POSITIVE LOGITS
     yourselves
    0.13
    ä½łèĩªå·±
    0.12
    able
    0.10
     yourself
    0.10
    ments
    0.09
    ability
    0.09
     fret
    0.09
    ÂŃing
    0.09
    äºĨåIJ§
    0.09
     Bradford
    0.08
    Activations Density 0.161%

    No Known Activations