© 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. 17894
    Prev
    Next
    INDEX
    Explanations

    animals

    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
    ä½ķåľ°
    -0.07
    缩水
    -0.07
    çī©
    -0.07
    abel
    -0.07
    ä¸İå®ŀè·µ
    -0.07
    è¿Ń
    -0.06
    人çī©
    -0.06
    anked
    -0.06
    çī©åĴĮ
    -0.06
    statt
    -0.06
    POSITIVE LOGITS
    åĢij
    0.10
    们çļĦ
    0.10
    们
    0.10
     ëĸ
    0.10
    ÑĮи
    0.09
    åĢijçļĦ
    0.09
    innen
    0.08
    ä»¬åľ¨
    0.08
     cái
    0.08
    esses
    0.08
    Activations Density 0.136%

    No Known Activations