© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    computer storage space

    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
     space
    -0.26
    æĹ¶ç©º
    -0.23
     spaces
    -0.23
    空éĹ´
    -0.22
    UCH
    -0.22
    åIJįåı«
    -0.22
    空éĸĵ
    -0.22
    æľīèĩªå·±çļĦ
    -0.22
    çļĦ空éĹ´
    -0.21
     spatial
    -0.21
    POSITIVE LOGITS
    /lic
    0.24
    ä¿ĥéĶĢ
    0.23
    -ra
    0.22
    @student
    0.22
    igators
    0.22
    åĴĮæĬĢæľ¯
    0.21
    zia
    0.21
    车åŃIJ
    0.20
    houses
    0.20
    ularity
    0.20
    Activations Density 0.009%

    No Known Activations