© 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. 14211
    Prev
    Next
    INDEX
    Explanations

    left, right, below

    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
    emma
    -0.07
    èµĭ
    -0.07
    èµĭäºĪ
    -0.07
    ÙĪÙĦÙĩ
    -0.06
    hm
    -0.06
     spelled
    -0.06
     Booker
    -0.06
     divers
    -0.06
    æī¿
    -0.06
    aders
    -0.06
    POSITIVE LOGITS
     views
    0.09
    å±ķ示äºĨ
    0.09
     view
    0.08
    ayscale
    0.08
    å±ķ示
    0.08
    views
    0.08
     illustrating
    0.08
     showing
    0.08
    ĥĿ
    0.08
    对æ¯Ķ
    0.08
    Activations Density 0.028%

    No Known Activations