© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56741
    Prev
    Next
    INDEX
    Explanations

    description of the related art

    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
    jax
    -0.08
    大åĮħ
    -0.08
    é«ĺä½İ
    -0.08
    blr
    -0.08
    gesund
    -0.08
    eming
    -0.08
    åıijå±ķåĪ°
    -0.08
    大åįĥ
    -0.08
    warts
    -0.08
    å±ĢçļĦ
    -0.08
    POSITIVE LOGITS
     Seoul
    0.08
    yeong
    0.08
    åľ¨éŁ©åĽ½
    0.08
     Korea
    0.08
     Korean
    0.08
    飩è¯Ń
    0.08
    é¦ĸå°Ķ
    0.08
     Jae
    0.08
     Choi
    0.07
    éŁ©åĽ½
    0.07
    Activations Density 0.303%

    No Known Activations