© 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. 49225
    Prev
    Next
    INDEX
    Explanations

    amazed at, amazing how

    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¸Ģå¹´
    -0.10
    设计çIJĨ念
    -0.09
    跨度
    -0.09
    æĺ¶
    -0.08
    æ¢Ń
    -0.08
     annex
    -0.08
    纵
    -0.08
    æĪªåĽ¾
    -0.08
    æģķ
    -0.08
    kop
    -0.08
    POSITIVE LOGITS
    æľīæŶåĢĻ
    0.13
    æľīæŶ
    0.12
    没æĥ³åĪ°
    0.09
    æľīå¤ļå°ij
    0.09
    orsch
    0.09
    åĵī
    0.09
     иногда
    0.09
    aban
    0.09
    èı½
    0.09
     sometimes
    0.08
    Activations Density 0.016%

    No Known Activations