© 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. 47745
    Prev
    Next
    INDEX
    Explanations

    citations like [@]

    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
    éĢĤ
    -0.09
    ifu
    -0.07
    igit
    -0.07
    è¾¾æĸ¯
    -0.07
    éļĶ
    -0.07
    kope
    -0.07
    egov
    -0.07
    éģ©
    -0.07
    ess
    -0.06
    Appear
    -0.06
    POSITIVE LOGITS
    ç°§
    0.08
    åij¨åħ¬
    0.08
    ä½łè¯´çļĦ
    0.07
    >Show
    0.07
    dung
    0.07
    å¦Ĥ梦
    0.07
    èļĤ
    0.07
    OrCreate
    0.07
    ļ
    0.07
    ä¸Ŀ
    0.07
    Activations Density 0.100%

    No Known Activations