© 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. 35129
    Prev
    Next
    INDEX
    Explanations

    easily + verb/adjective

    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
    еÑĤÑĮ
    -0.10
    pile
    -0.09
    ä¸įå¾Ĺå·²
    -0.09
    ä¸Ģèµ·
    -0.08
    鼩
    -0.08
    æĮł
    -0.08
    é«ĺæ¸ħ
    -0.08
    ãĤĴæĮģãģ¤
    -0.08
    åħ±åIJĮåĬªåĬĽ
    -0.08
     uncon
    -0.08
    POSITIVE LOGITS
     dÃłng
    0.12
    忽çķ¥
    0.09
    CHA
    0.09
    Ĭ
    0.08
    udget
    0.08
     togg
    0.08
    çľĭåĩº
    0.08
    omer
    0.08
    iad
    0.08
    iated
    0.08
    Activations Density 0.013%

    No Known Activations