© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37471
    Prev
    Next
    INDEX
    Explanations

    positive adjectives followed by nouns or continuations

    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
    azes
    -0.10
    éľģ
    -0.09
    éĥ½æľīèĩªå·±
    -0.09
    èĥ¼
    -0.09
    ä¹Łæĺ¯å¦ĤæѤ
    -0.09
    appl
    -0.08
    æ§Ľ
    -0.08
    ober
    -0.08
    ury
    -0.08
    æĸ°æĬĢæľ¯
    -0.08
    POSITIVE LOGITS
    åĤįæĻļ
    0.09
    é¢ĩ
    0.09
    çŁ£
    0.09
    -rounded
    0.09
    ä¸į失
    0.09
    monic
    0.09
    åĪĿæŃ¥
    0.09
    ERIC
    0.09
    çļĦæķĪæŀľ
    0.09
    æĥ¬
    0.09
    Activations Density 0.081%

    No Known Activations