© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6054
    Prev
    Next
    INDEX
    Explanations

    adjective suffixes

    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
    éĥ½æľīçĿĢ
    -0.10
    çĸĥ
    -0.10
    使ä¹ĭ
    -0.09
    éĩijå±±
    -0.09
    swire
    -0.09
    èµ°åħ¥
    -0.09
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.09
    ä½Ĩè¿Ļ
    -0.09
    è¿Ļä¸įæĺ¯
    -0.09
    prior
    -0.09
    POSITIVE LOGITS
    ly
    0.14
    ìłģìĿ¸
    0.13
    ä¸įéĶĻçļĦ
    0.13
    fully
    0.12
    ful
    0.12
    ous
    0.12
    ingly
    0.12
    æĢ§çļĦ
    0.11
    ably
    0.11
    ously
    0.11
    Activations Density 0.169%

    No Known Activations