© 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. 2886
    Prev
    Next
    INDEX
    Explanations

    too much or exaggerated

    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´»
    -0.09
    å°±æĺ¯åľ¨
    -0.09
    fund
    -0.09
    å®ģ
    -0.09
    uzzi
    -0.09
    åIJ¯è¿ª
    -0.08
    è§Ħå¾ĭ
    -0.08
    红æĹĹ
    -0.08
    åįĩåѦ
    -0.08
    ìŀĺ
    -0.08
    POSITIVE LOGITS
    åĵī
    0.10
    æ´½
    0.09
     Pence
    0.09
    ansom
    0.09
    zac
    0.08
     atol
    0.08
    汶
    0.08
    è´¯éĢļ
    0.08
    åģ¶å°Ķ
    0.08
    åįķåįķ
    0.08
    Activations Density 0.027%

    No Known Activations