© 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. 521
    Prev
    Next
    INDEX
    Explanations

    age

    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
    еÑģÑĤеÑģÑĤвенн
    -0.24
     Canary
    -0.22
    индивид
    -0.21
     effic
    -0.20
    å®Įæķ´
    -0.20
    mor
    -0.20
    è§ģéĿ¢
    -0.20
    楼å®ĩ
    -0.20
    пÑĢоÑĦеÑģÑģионал
    -0.20
    благо
    -0.19
    POSITIVE LOGITS
     fashioned
    0.26
    -fashioned
    0.26
    çļĦåŃ©åŃIJ
    0.25
    stamp
    0.24
    -age
    0.23
    åĴĮ社ä¼ļ
    0.23
    ["$
    0.22
    åĴĮæĬĢæľ¯
    0.22
    /time
    0.22
    (age
    0.22
    Activations Density 0.055%

    No Known Activations