© 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. 31313
    Prev
    Next
    INDEX
    Explanations

    will be X / will X / ’ll be X

    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»Ģä¹Īåij¢
    -0.11
    忽çĦ¶
    -0.09
    ież
    -0.09
    ç«ĭ项
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.09
    è¶Ĭæĺ¯
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
    éĻįèĩ³
    -0.08
    åIJĪä½ľåħ±èµ¢
    -0.08
    TOP
    -0.08
    POSITIVE LOGITS
    寻æī¾
    0.11
    çĶ¨å¿ĥ
    0.10
    åĬªåĬĽ
    0.10
    èĢĥéªĮ
    0.09
    åĬĽæ±Ĥ
    0.09
    大éĥ¨åĪĨ
    0.09
    å·Ŀ
    0.09
    ups
    0.08
     FU
    0.08
    åĬĽäºī
    0.08
    Activations Density 0.027%

    No Known Activations