© 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. 33814
    Prev
    Next
    INDEX
    Explanations

    existence or presence

    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
    æĢĿ绪
    -0.09
    ombre
    -0.09
    讯
    -0.09
    ä¸ĢæĿ¯
    -0.09
    edes
    -0.08
     ÑģебÑı
    -0.08
    è£ħå¤ĩåĪ¶éĢł
    -0.08
    trak
    -0.08
    æºĺ
    -0.08
    ç»Ĩå¿ĥ
    -0.08
    POSITIVE LOGITS
    ential
    0.12
    侥幸
    0.11
    æĺİæĺ¾çļĦ
    0.11
    entially
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    ive
    0.10
    å·²ä¹ħçļĦ
    0.09
    мо
    0.09
     ÙĦدÙī
    0.09
    /do
    0.09
    Activations Density 0.049%

    No Known Activations