© 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. 23727
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and pronouns

    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
    åĮĨ
    -0.09
    ichen
    -0.08
    èĭĩ
    -0.08
     Bars
    -0.08
    å±±æĿij
    -0.08
    éŀĺ
    -0.07
     Shaman
    -0.07
     Qin
    -0.07
    çī¹
    -0.07
    kind
    -0.07
    POSITIVE LOGITS
    å¼łè´´
    0.10
    éĻ¢éĻ¢å£«
    0.10
    ä¹Ŀåįģ
    0.10
    ç½ij讯
    0.10
    uju
    0.09
    åħ¥é©»
    0.09
    æģĤ
    0.09
    arcy
    0.09
    æīįå¹²
    0.09
    æķ°é¢Ŀ
    0.09
    Activations Density 0.042%

    No Known Activations