© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 1861
    Prev
    Next
    INDEX
    Explanations

    bar, desk, island, reception

    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
    ckeditor
    -0.24
    å¾Ģå¹´
    -0.24
    dbl
    -0.23
    comfort
    -0.23
    è°ĭ
    -0.22
    管çIJĨå±Ģ
    -0.21
    åºĶæĢ¥é¢Ħæ¡Ī
    -0.21
    UNG
    -0.21
    gba
    -0.21
    strup
    -0.21
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.30
    æŁľåı°
    0.29
    -style
    0.27
    ä¸Ģä¾§
    0.27
    è´§æŀ¶
    0.25
    -side
    0.25
    ä¸Ĭåīį
    0.25
    å¼ı
    0.24
    ä½įç½®
    0.24
    ä¸Ĭæľī
    0.24
    Activations Density 0.012%

    No Known Activations