© 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. 22535
    Prev
    Next
    INDEX
    Explanations

    abnormalities and stiffness in

    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
    åºĬä½į
    -0.10
    è·Ĺ
    -0.09
     ÑĦоÑĢ
    -0.09
    å°Ķæĸ¯
    -0.09
    èĩ´çĻĮ
    -0.09
    OSH
    -0.09
     наÑĢ
    -0.09
    ÑģÑĤавлен
    -0.08
    æīĢ产çĶŁçļĦ
    -0.08
    稿
    -0.08
    POSITIVE LOGITS
     measures
    0.10
    è½»
    0.09
    features
    0.08
    çī¹å¾ģ
    0.08
    ksam
    0.08
     features
    0.08
    迹象
    0.08
    çī¹çĤ¹
    0.08
    è¼ķ
    0.08
    åĬłå¿«æİ¨è¿Ľ
    0.08
    Activations Density 2.444%

    No Known Activations