© 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. 64810
    Prev
    Next
    INDEX
    Explanations

    soft silicone, Cal Look, Life Science, Best of NumisWiki, locating the game, three generations, tier 90 plastic

    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
    ÑģÑĤе
    -0.07
    -0.06
    ť
    -0.06
    âĢ¦
    -0.06
    ...
    -0.05
    士æŀĹ
    -0.05
    ails
    -0.05
    thon
    -0.05
    ewise
    -0.05
    ex
    -0.05
    POSITIVE LOGITS
    çĩ
    0.08
    ç¯ĩäºĮ
    0.08
    áĢĦáĢº
    0.07
    TAG
    0.07
    ×Ļק
    0.07
    ynos
    0.07
    çĶŁäº§å»ºè®¾
    0.07
    견
    0.07
     méc
    0.07
    ulat
    0.07
    Activations Density 0.198%

    No Known Activations