© 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. 9581
    Prev
    Next
    INDEX
    Explanations

    thin, light, low power, contrast

    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
    åĬ£
    -0.09
    åį·
    -0.09
    å·¾
    -0.08
    ÑĪиб
    -0.08
    èģļ
    -0.08
    梯
    -0.08
    åĮĹæĸ¹
    -0.08
     ÑĤÑĢеÑĤÑĮ
    -0.08
     ÑĢазвива
    -0.08
     Cha
    -0.08
    POSITIVE LOGITS
    羣çļ®
    0.11
    åįĵè¶Ĭ
    0.11
    èĩ»
    0.10
    çªĦ
    0.10
    æŀģèĩ´
    0.10
    èĢĻ
    0.10
    Ñģен
    0.09
    大å¹ħæıIJåįĩ
    0.09
    åŀł
    0.09
    æĺŁçº§
    0.09
    Activations Density 0.088%

    No Known Activations