© 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. 27374
    Prev
    Next
    INDEX
    Explanations

    light and illumination

    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
    æ¶ĪåĮĸ
    -0.10
    æµģ产
    -0.10
    稳åģ¥
    -0.09
    çĵľ
    -0.09
     Ñĥни
    -0.08
    åĺ´éĩĮ
    -0.08
    avage
    -0.08
    _quad
    -0.08
    ķìĿ¸
    -0.08
    ivalent
    -0.08
    POSITIVE LOGITS
    çħ§æĺİ
    0.22
    çħ§äº®
    0.22
    çģ¯
    0.19
    åħī线
    0.19
    亮度
    0.19
     ÑģвеÑĤ
    0.18
    çģ¯åħ·
    0.18
    åħīæºIJ
    0.18
    çģ¯åħī
    0.18
     light
    0.18
    Activations Density 0.157%

    No Known Activations