© 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. 27018
    Prev
    Next
    INDEX
    Explanations

    syndrome

    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
    沧æ¡ij
    -0.10
    鸩
    -0.10
    çĶŁæĹ¥
    -0.09
    æīĢåģļçļĦ
    -0.09
     полÑĮзÑĥ
    -0.09
    oscope
    -0.09
    ç½ħ
    -0.09
    ç¨Ĺ
    -0.09
     ApplicationException
    -0.09
    .Classes
    -0.09
    POSITIVE LOGITS
     syndrome
    0.13
     Syndrome
    0.11
    综åIJĪå¾ģ
    0.10
    åĩ¶
    0.08
    åĪĨ离
    0.08
    è¿Ļæĺ¯ä¸Ģç§į
    0.08
    Impl
    0.08
    lord
    0.08
     type
    0.08
    åıĪ称
    0.08
    Activations Density 0.932%

    No Known Activations