© 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. 4432
    Prev
    Next
    INDEX
    Explanations

    specific suffix '-ity'

    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
    lein
    -0.10
    lace
    -0.10
    åĽĽå¤§
    -0.10
    laus
    -0.10
    _fid
    -0.09
    IZE
    -0.09
    ize
    -0.09
    cale
    -0.09
    åħĪè¡Į
    -0.08
    à¹Ĥà¸Ĭ
    -0.08
    POSITIVE LOGITS
    ä½łçľĭ
    0.07
    社ä¼ļ责任
    0.07
     enlist
    0.07
    é¦Ħ
    0.07
    è·¯ä¸Ĭ
    0.07
    é²Ĭ
    0.07
    æ¤ħ
    0.07
    é³ĸ
    0.07
    æĦŁåıĹåĪ°äºĨ
    0.07
    åħ¬åı¸ç«łç¨ĭ
    0.07
    Activations Density 1.684%

    No Known Activations