© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10753
    Prev
    Next
    INDEX
    Explanations

    after or post

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fle
    -0.07
    åģ¶
    -0.07
    常年
    -0.07
    åģ¶çĦ¶
    -0.07
    é¢Ħç¥Ŀ
    -0.06
    åĩĿç¥ŀ
    -0.06
    éĢĤ
    -0.06
    annot
    -0.06
     intercept
    -0.06
     Prov
    -0.06
    POSITIVE LOGITS
     post
    0.21
     pós
    0.20
     pasca
    0.18
    æĪĺåIJİ
    0.18
     after
    0.17
    after
    0.17
    post
    0.16
    (post
    0.16
     Post
    0.16
    æľ¯åIJİ
    0.16
    Activations Density 0.744%

    No Known Activations