© 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. 1454
    Prev
    Next
    INDEX
    Explanations

    GameStick, MSBuild, Yaoguai, viscolin, UEFI

    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
    èĪ¬
    -0.26
    æĺ¯
    -0.25
    nts
    -0.23
    å®ģ
    -0.23
    âĻĤ
    -0.22
    çIJĨ
    -0.22
    çĶ±
    -0.22
    }
    -0.21
    头
    -0.21
     Ud
    -0.21
    POSITIVE LOGITS
     #↵↵
    0.28
    -Col
    0.26
    [],↵
    0.24
    documentation
    0.23
    [];↵↵
    0.23
    perf
    0.22
    pole
    0.22
     [];↵↵
    0.22
     ngữ
    0.22
    åľ°ä¸ĭ室
    0.22
    Activations Density 0.066%

    No Known Activations