© 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. 38909
    Prev
    Next
    INDEX
    Explanations

    multipliers and ratios

    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
    tage
    -0.08
    åĩ
    -0.08
    agar
    -0.08
    onga
    -0.08
    æİīçļĦ
    -0.08
    æĴ
    -0.07
    ä»
    -0.07
    ongan
    -0.07
    lak
    -0.07
     sâu
    -0.07
    POSITIVE LOGITS
    åĢįçļĦ
    0.12
    åĢį
    0.11
    çĻ¾åĢį
    0.10
     ratio
    0.09
     ratios
    0.09
    åĢįå¢ŀ
    0.09
    åĢįæķ°
    0.09
    åĢį以ä¸Ĭ
    0.08
    ä¸ĢåĢį
    0.08
     Ratio
    0.08
    Activations Density 0.023%

    No Known Activations