© 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. 64060
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun

    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
    Negative Logits
    éĻŁ
    -0.11
    è¿Ļä¸ĢçĤ¹
    -0.10
    ánt
    -0.10
    ä¸Ģå¼Ģå§ĭå°±
    -0.10
    BootApplication
    -0.10
    \Bridge
    -0.10
    uran
    -0.09
    å·¥ä½ľç«Ļ
    -0.09
    海滨
    -0.09
    hammer
    -0.09
    POSITIVE LOGITS
    ams
    0.07
    è¿ĺ
    0.07
    æķ£
    0.07
    osto
    0.07
    S
    0.07
    л
    0.07
    è·¨åĽ½
    0.07
    ç»Ī身
    0.07
     ???
    0.06
    usa
    0.06
    Activations Density 0.611%

    No Known Activations