© 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. 16950
    Prev
    Next
    INDEX
    Explanations

    general, specific, pragmatic, simplistic, extensive, clear

    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
    å¤ļä¹Ī
    -0.08
    /animations
    -0.08
     notoriously
    -0.07
    éļIJèĹıçļĦ
    -0.07
    zend
    -0.07
    大æľī
    -0.07
    inde
    -0.07
     certa
    -0.07
     certain
    -0.07
    çļĦ巨大
    -0.07
    POSITIVE LOGITS
    -ish
    0.10
     approach
    0.09
     explanation
    0.09
    ä¸ĢçĤ¹çļĦ
    0.07
    lest
    0.07
     reasoning
    0.07
     analysis
    0.07
     examples
    0.07
     approaches
    0.07
     yet
    0.07
    Activations Density 0.092%

    No Known Activations