© 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. 27777
    Prev
    Next
    INDEX
    Explanations

    mathematical or code delimiters

    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
     пÑĢикоÑĢ
    -0.08
    osan
    -0.08
    alani
    -0.08
    unami
    -0.08
    entif
    -0.08
    otra
    -0.08
    à¸ģลà¸ĩ
    -0.08
    кла
    -0.07
    VML
    -0.07
    feder
    -0.07
    POSITIVE LOGITS
     Ast
    0.07
     ast
    0.07
    Ast
    0.06
     vies
    0.06
    å®ļ
    0.06
    åĢ¼å¾Ĺ
    0.06
    side
    0.06
     vie
    0.06
    åįĥéĩij
    0.06
    asted
    0.05
    Activations Density 0.001%

    No Known Activations