© 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. 60794
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    atoires
    -0.07
     struggles
    -0.06
    åĿ¦çĦ¶
    -0.06
     dile
    -0.06
    isons
    -0.06
    ξÏį
    -0.06
    ä¸Ģè¾Ī
    -0.06
     suivant
    -0.06
    ç®Ģ称
    -0.06
    仪
    -0.06
    POSITIVE LOGITS
    è¹´
    0.09
     (!
    0.09
    ochen
    0.08
    (?)
    0.08
    å±Ĭæ¯ķä¸ļçĶŁ
    0.08
    (!
    0.08
     (?)
    0.08
    ä¸įåºĶæ±Ĥ
    0.07
    çĭ©
    0.07
    ìĹĨìĿ´
    0.07
    Activations Density 0.695%

    No Known Activations