© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    Copyright, Search, Profile

    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
    è¿Ļæĸ¹éĿ¢
    -0.08
     Thr
    -0.07
    çŃīçŃī
    -0.07
    ast
    -0.07
    -0.07
    les
    -0.07
     both
    -0.07
    -0.07
    ola
    -0.07
    åij¨æģ©
    -0.07
    POSITIVE LOGITS
    çļ±
    0.10
    æĸ°æĶ¿
    0.10
    çıº
    0.10
    缤纷
    0.10
    éĥ¨åĪĨåľ°åĮº
    0.09
     ÑĢÑĥков
    0.09
    大çĽĺ
    0.09
    индивид
    0.09
    æ¾¹
    0.09
    двиг
    0.09
    Activations Density 0.830%

    No Known Activations