© 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. 17490
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons

    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
    åĿıçļĦ
    -0.07
     agu
    -0.07
     intensa
    -0.07
    ong
    -0.07
    æĶ¾å¤§
    -0.07
    æıŃ
    -0.06
    ik
    -0.06
    çĤ¯
    -0.06
    Tag
    -0.06
    大å¹ħæıIJåįĩ
    -0.06
    POSITIVE LOGITS
     (>
    0.09
     suppressing
    0.09
    Leod
    0.08
    ç¨Ģçĸı
    0.08
    Ø´ÙĪ
    0.08
    OSE
    0.08
    ivio
    0.08
    chau
    0.08
     suppress
    0.07
    ç¨Ģ
    0.07
    Activations Density 0.096%

    No Known Activations