© 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. 17319
    Prev
    Next
    INDEX
    Explanations

    first, before then

    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
    没äºĭ
    -0.10
    没æľīä»Ģä¹Ī
    -0.09
    没æľī人
    -0.08
    åľ¨åľ°ä¸Ĭ
    -0.08
    ifest
    -0.08
    åĬ¨éĿĻ
    -0.08
    åĨįåĪ°
    -0.08
     Mein
    -0.08
    宣åijĬ
    -0.08
    ä¹Łä¸įçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    åħĪ
    0.13
    åīįæıIJæĺ¯
    0.10
    udit
    0.09
    åīįæıIJ
    0.09
    è¦ģåĬłå¼º
    0.09
     intervening
    0.09
    oday
    0.09
    ä¸ŃéĹ´
    0.09
    å¾Ĺèµ·
    0.09
    å¹Į
    0.09
    Activations Density 0.022%

    No Known Activations