© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 702
    Prev
    Next
    INDEX
    Explanations

    a bit of

    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
    åIJĦ个çݯèĬĤ
    -0.23
    ä¸įæĸŃæıIJé«ĺ
    -0.23
    whatever
    -0.23
    åĴĮæĶ¯æĮģ
    -0.22
     whatever
    -0.22
    æīĢæıIJä¾Ľ
    -0.22
     whoever
    -0.22
    éĤ£æŶ
    -0.22
    æѤåIJİ
    -0.21
    ä¹ĭæīĢ
    -0.21
    POSITIVE LOGITS
     overlap
    0.30
     luck
    0.24
     controversy
    0.23
    ä¾ĭå¤ĸ
    0.23
     reflection
    0.23
     flair
    0.23
     workaround
    0.23
    ìĶ©
    0.23
     uncertainty
    0.22
     breeze
    0.22
    Activations Density 0.008%

    No Known Activations