© 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. 10681
    Prev
    Next
    INDEX
    Explanations

    should followed by verbs

    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
    忽
    -0.09
    æĦ¿æĦı
    -0.09
     pard
    -0.09
     Geb
    -0.08
    LAB
    -0.08
    ãģ¿ãģª
    -0.08
    pars
    -0.08
    å¹³å®ī
    -0.08
    èħĶ
    -0.08
    ìĽIJ
    -0.08
    POSITIVE LOGITS
    åģ¶åĥı
    0.10
    ä¸į该
    0.10
    ä¸įåºĶ该
    0.09
    igne
    0.09
    åIJİåĭ¤
    0.09
    /Page
    0.09
     eigentlich
    0.09
    俦
    0.09
    æł¹æį®
    0.09
    èŁ¾
    0.08
    Activations Density 0.083%

    No Known Activations