© 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. 2592
    Prev
    Next
    INDEX
    Explanations

    proper nouns in titles

    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
    htar
    -0.07
    个大
    -0.07
     matrim
    -0.06
    åıĭæĥħ
    -0.06
     Termin
    -0.06
    λικ
    -0.06
    她çİ°åľ¨
    -0.06
    ç¨įç¨į
    -0.06
    loh
    -0.06
    :UI
    -0.06
    POSITIVE LOGITS
    ovo
    0.08
    onos
    0.08
    ä¸ŃåĽ½å®¶
    0.08
     famously
    0.08
     contemporary
    0.08
    笳
    0.07
     contempor
    0.07
    edu
    0.07
    ä¸İçݰ代
    0.07
    enf
    0.07
    Activations Density 0.308%

    No Known Activations