© 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. 23857
    Prev
    Next
    INDEX
    Explanations

    places or times

    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
    æ¹Ħ
    -0.10
    erten
    -0.09
    äºĮåŃĹ
    -0.09
    æĭ§
    -0.08
    æ´»åĬ¨çİ°åľº
    -0.08
    大åĬĽåıijå±ķ
    -0.08
    åĩºå·®
    -0.08
    _SHA
    -0.08
    eti
    -0.08
    ry
    -0.08
    POSITIVE LOGITS
     Wal
    0.09
    vsp
    0.09
    åĴĮ个人
    0.09
    ä¸Ģ对ä¸Ģ
    0.08
    å½ĵåľ°äºº
    0.08
    ä¸Ģèµ·æĿ¥
    0.08
    _globals
    0.08
    íĮ¬
    0.08
    å´Ł
    0.08
    ä¾Ľæ°´
    0.08
    Activations Density 0.153%

    No Known Activations