© 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. 3363
    Prev
    Next
    INDEX
    Explanations

    advances in, changes in, loss of

    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
    缮çļĦåľ¨äºİ
    -0.11
    éĢłæĪIJçļĦ
    -0.11
    ä¹į
    -0.10
    åĩºèº«
    -0.10
    ãģĬãģĭãģĴ
    -0.10
    æ¬ł
    -0.09
    æıIJåĩºçļĦ
    -0.09
    stride
    -0.09
     thức
    -0.09
     ÑĢолÑĮ
    -0.09
    POSITIVE LOGITS
    æĽ´å¿«
    0.10
    äºĨä¸Ģåľº
    0.10
    产çĶŁ
    0.10
     поÑı
    0.10
    ä¸Ģç³»åĪĹ
    0.09
    æ¶Ł
    0.09
    家åĸ»æĪ·æĻĵ
    0.08
     Parm
    0.08
    å¨ĥå¨ĥ
    0.08
    æĽ´å¤ļçļĦ
    0.08
    Activations Density 0.248%

    No Known Activations