© 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. 7627
    Prev
    Next
    INDEX
    Explanations

    successful verification

    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
    agos
    -0.10
    cesi
    -0.09
     inilah
    -0.08
    /entity
    -0.08
    agas
    -0.08
    askell
    -0.08
    -entity
    -0.08
    âĢ¦]
    -0.08
    çŁ¥ä¹ĭ
    -0.08
    æľīæīĢæĢĿ
    -0.08
    POSITIVE LOGITS
    tere
    0.06
    çĴ§
    0.06
    æŀģäºĨ
    0.06
    spacer
    0.06
    èĢĮ对äºİ
    0.06
    举
    0.05
    azed
    0.05
     because
    0.05
    ç»
    0.05
    ä¸¤æ±Ł
    0.05
    Activations Density 0.040%

    No Known Activations