© 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. 2000
    Prev
    Next
    INDEX
    Explanations

    time and dates

    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
    èĦī
    -0.09
    omp
    -0.09
     dej
    -0.09
    温åĴĮ
    -0.09
    -pt
    -0.09
    渴
    -0.08
     PT
    -0.08
    åħ¬è®¤
    -0.08
    éĢł
    -0.08
    PT
    -0.08
    POSITIVE LOGITS
    ä½ķæŶ
    0.12
    ä»Ģä¹ĪæŶåĢĻ
    0.12
    åīįæĻ¯
    0.11
    Enumeration
    0.10
    è¦ģä¸įçĦ¶
    0.10
    /docs
    0.10
    å½ĴæĿ¥
    0.10
     ìķŀìľ¼ë¡ľ
    0.10
    ä¸ĭ次
    0.10
    å¤ļä¹ħ
    0.09
    Activations Density 0.047%

    No Known Activations