© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    social links

    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
    budget
    -0.25
     Budget
    -0.25
     sequ
    -0.24
     Serie
    -0.24
     serie
    -0.23
     budget
    -0.23
    é¢Ħç®Ĺ
    -0.22
    æ¡ģ
    -0.22
    êu
    -0.21
    æĮ«æĬĺ
    -0.21
    POSITIVE LOGITS
     linking
    0.27
     links
    0.26
    ç»İ
    0.24
    ãĥªãĥ³ãĤ¯
    0.23
    urch
    0.23
    /rss
    0.23
     Links
    0.22
    社交åªĴä½ĵ
    0.22
    Thought
    0.22
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    0.22
    Activations Density 0.001%

    No Known Activations