© 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. 49654
    Prev
    Next
    INDEX
    Explanations

    little [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
    Not in Any Lists

    No Comments

    Negative Logits
    çī¹æľĹ
    -0.11
    éļ¾è¿ĩ
    -0.10
    大åݦ
    -0.10
    ç§ijå°Ķ
    -0.10
    äºĨä¸Ģ声
    -0.09
     downright
    -0.09
    ä¸Ģ个èģĮä¸ļ
    -0.09
    大åĴĸ
    -0.09
    compass
    -0.09
    ä¹ĭ声
    -0.09
    POSITIVE LOGITS
    ish
    0.11
    ishly
    0.09
    atches
    0.08
    zelf
    0.08
    entially
    0.08
    åīĤ
    0.08
    ëħIJ
    0.08
     Cher
    0.08
    åĢ¡
    0.08
    pdata
    0.08
    Activations Density 0.019%

    No Known Activations