© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19893
    Prev
    Next
    INDEX
    Explanations

    not

    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
    åĪº
    -0.09
    éĺĶ
    -0.08
    å¿ı
    -0.08
    设计çIJĨ念
    -0.08
     Hyper
    -0.08
     defenses
    -0.08
    geries
    -0.08
    .isEnabled
    -0.08
    oret
    -0.08
    orro
    -0.08
    POSITIVE LOGITS
    楼ä¸Ĭ
    0.10
    æĦıåij³çĿĢ
    0.10
    并ä¸į代表
    0.10
    æłĩå¿ĹçĿĢ
    0.09
    çīĮçħ§
    0.09
    并ä¸įæĦıåij³
    0.09
    注æĺİæĿ¥æºIJ
    0.09
    éļ¶å±ŀ
    0.09
    åı¹äºĨ
    0.09
     éc
    0.09
    Activations Density 0.017%

    No Known Activations