© 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. 606
    Prev
    Next
    INDEX
    Explanations

    ;

    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
     nämlich
    -0.25
    éĤ£ç§į
    -0.24
    æĺ¯å¤ļä¹Ī
    -0.23
    åĴĮå®ĮåĸĦ
    -0.23
    ä»Ģä¹Īåij¢
    -0.22
    ç»ıéªĮåĴĮ
    -0.22
    è¿Ļ个æĹ¶ä»£
    -0.22
    cis
    -0.22
    æīĢæıIJä¾Ľä¹ĭ
    -0.22
    éĤ£ä»½
    -0.21
    POSITIVE LOGITS
     Possible
    0.27
    Possible
    0.25
     Need
    0.25
     E
    0.24
     P
    0.23
     Monkey
    0.23
     Ultimate
    0.22
     possible
    0.22
     Multiple
    0.22
    åħ¶å®ĥ
    0.22
    Activations Density 0.044%

    No Known Activations