© 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. 39563
    Prev
    Next
    INDEX
    Explanations

    software licenses and SDKs

    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
    üh
    -0.07
    æį§çĿĢ
    -0.07
    QUENCY
    -0.07
    éķ¿éķ¿
    -0.07
    aje
    -0.07
     prezi
    -0.07
    è¿ĻæŶçļĦ
    -0.07
    WithContext
    -0.07
     POLITICO
    -0.06
    ader
    -0.06
    POSITIVE LOGITS
     Version
    0.10
     version
    0.08
    лаÑģ
    0.08
    (tm
    0.07
    pired
    0.07
    	http
    0.07
    æľīæѤ
    0.07
     Portable
    0.07
    .googlecode
    0.07
     http
    0.07
    Activations Density 1.441%

    No Known Activations