© 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. 62603
    Prev
    Next
    INDEX
    Explanations

    ® or TM trademarks

    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
    EMAIL
    -0.08
    ikh
    -0.07
    è¡
    -0.07
     defs
    -0.07
    kest
    -0.06
    elage
    -0.06
    以赴
    -0.06
     ë¶ĢíĦ°
    -0.06
    oor
    -0.06
    ermen
    -0.06
    POSITIVE LOGITS
    ®
    0.21
    ®,
    0.18
    âĦ¢
    0.17
     ®
    0.16
    (tm
    0.10
    ©
    0.10
    TM
    0.10
    ç³»åĪĹ产åĵģ
    0.09
     âĦ
    0.09
    (TM
    0.09
    Activations Density 0.378%

    No Known Activations