© 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. 29774
    Prev
    Next
    INDEX
    Explanations

    maximum variation sampling

    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
    ä¸Ģä½ĵ
    -0.07
    çŁŃæļĤ
    -0.07
    åĵªé¡¹
    -0.07
    æĹłæķ°
    -0.06
    CharArray
    -0.06
    ><![
    -0.06
    çļĦ绣ä¸Ģ
    -0.06
    ivot
    -0.06
    ibble
    -0.06
    çĭ©
    -0.06
    POSITIVE LOGITS
     representative
    0.13
    代表æĢ§çļĦ
    0.13
    çļĦ代表
    0.12
    代表æĢ§
    0.12
     mewakili
    0.11
    Represent
    0.11
     representatives
    0.11
     Representative
    0.10
    代表äºĨ
    0.10
    represent
    0.10
    Activations Density 0.218%

    No Known Activations