© 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. 26647
    Prev
    Next
    INDEX
    Explanations

    protective cases and covers

    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
    èµŀ
    -0.09
    å§ĭ
    -0.09
     hole
    -0.09
    éĮ¾
    -0.09
    åīĶ
    -0.09
    åįł
    -0.08
     Thảo
    -0.08
    æ¢ħ
    -0.08
     holes
    -0.08
     Hole
    -0.08
    POSITIVE LOGITS
    è¦ĨçĽĸ
    0.18
    ä¿ĿæĬ¤
    0.18
     cover
    0.16
    罩
    0.16
    ä¸Ģå±Ĥ
    0.15
    åºĩ
    0.15
    ä¿ĿèŃ·
    0.15
    åĮħ裹
    0.15
    Cover
    0.15
    -cover
    0.15
    Activations Density 0.158%

    No Known Activations