© 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. 49010
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by specific nouns

    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¨Ł
    -0.09
    表达äºĨ
    -0.09
    cam
    -0.09
    èĻļæŀĦ
    -0.09
    ä¸ĢåĪĻ
    -0.09
    åĥ®
    -0.08
    æ¸ł
    -0.08
    æĤŃ
    -0.08
    jur
    -0.08
     fict
    -0.08
    POSITIVE LOGITS
    åľ°ä¸Ń
    0.10
    ness
    0.09
    ties
    0.08
    æĮŀ
    0.08
    inery
    0.08
    ipse
    0.08
    NESS
    0.08
    ismo
    0.08
    å°ijäºĨ
    0.08
    ofday
    0.08
    Activations Density 0.540%

    No Known Activations