© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1985
    Prev
    Next
    INDEX
    Explanations

    speed and acceleration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    涤
    -0.28
    以为
    -0.26
    eteor
    -0.24
    æ»ĭåħ»
    -0.24
     anonymously
    -0.24
    èį¼
    -0.23
    è¿Ļä¸Ģå¹´
    -0.23
    éķ¶åµĮ
    -0.23
    åħľ
    -0.23
     concurrently
    -0.23
    POSITIVE LOGITS
     quicker
    0.39
    /fast
    0.36
    å¿«éĢŁ
    0.35
     startup
    0.35
    è¿ħéĢŁ
    0.35
     quickest
    0.35
    æĽ´å¿«
    0.33
     fastest
    0.33
    éĢŁåº¦
    0.33
    éĢŁåº¦å¿«
    0.33
    Activations Density 0.096%

    No Known Activations