© 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. 36066
    Prev
    Next
    INDEX
    Explanations

    dedicated server or service

    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¿ĩåİ»çļĦ
    -0.09
    IsActive
    -0.08
    çĥ«
    -0.08
     Gian
    -0.08
    æĦ¿
    -0.08
    _trap
    -0.08
    æ¬Ĭ
    -0.08
    ISCO
    -0.08
     Timothy
    -0.08
    tras
    -0.08
    POSITIVE LOGITS
    ä¸ĵéŨ
    0.19
    ä¸ĵçĶ¨
    0.18
     dedicated
    0.17
    ä¸ĵ人
    0.16
    ä¸ĵ
    0.15
     Dedicated
    0.15
    ä¸ĵå±ŀ
    0.14
    å°Ī
    0.14
     dedicate
    0.12
    ä¸ĵèģĮ
    0.12
    Activations Density 0.038%

    No Known Activations