© 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. 33934
    Prev
    Next
    INDEX
    Explanations

    economies and resources

    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
    ä¸ĭæĿ¥
    -0.11
    åıµ
    -0.10
    çĶŁæ´»æ°´å¹³
    -0.10
    ÑģлÑĥж
    -0.09
    åĢŁåı£
    -0.09
    åĸľæĤ¦
    -0.09
    unami
    -0.09
    анÑĤ
    -0.09
    èĩªè±ª
    -0.09
    ä¹ı
    -0.09
    POSITIVE LOGITS
    å¾Ĺ天
    0.10
    åĿĩè¡¡
    0.09
    åī¯
    0.09
    Seen
    0.09
    äºĤ
    0.09
    èµĦæºIJéħįç½®
    0.09
    ä¹±
    0.08
    å¸Ĥåł´
    0.08
    amina
    0.08
     market
    0.08
    Activations Density 0.036%

    No Known Activations