© 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. 60996
    Prev
    Next
    INDEX
    Explanations

    abstract nouns followed by subjects

    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
    forme
    -0.10
    æľīæĽ´å¤ļçļĦ
    -0.09
    åĮĸçŁ³
    -0.09
    ç¼£
    -0.09
    ktop
    -0.09
    /vendors
    -0.09
    illard
    -0.09
    çĭ·
    -0.08
    ìłĢ
    -0.08
    æĺ¯ä¸Ģ件
    -0.08
    POSITIVE LOGITS
     they
    0.16
    æĪijä»¬åľ¨
    0.16
     you
    0.15
    ä»ĸ们
    0.15
     we
    0.15
    æĪijè¦ģ
    0.15
    æĪijåľ¨
    0.14
    æĪij们
    0.13
    æĪijåĢij
    0.12
    ä¼Ĺ人
    0.12
    Activations Density 0.386%

    No Known Activations