© 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. 14971
    Prev
    Next
    INDEX
    Explanations

    New York, Avenue, AL

    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
    æĹ¶å¯¹
    -0.07
    uml
    -0.07
    IOC
    -0.07
    .mix
    -0.07
    ynet
    -0.06
    çİĩè¾¾
    -0.06
    Infinity
    -0.06
    OST
    -0.06
    allo
    -0.06
    æĸ¹æŃ£
    -0.06
    POSITIVE LOGITS
     arbitrary
    0.07
    å®Ľ
    0.06
    ENTITY
    0.06
    ÙĪار
    0.06
    osite
    0.06
    sWith
    0.06
    çij
    0.06
     Noten
    0.06
    oplevel
    0.06
    hood
    0.06
    Activations Density 0.001%

    No Known Activations