© 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. 19363
    Prev
    Next
    INDEX
    Explanations

    category theory, mathematics, science notation

    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
    orgh
    -0.06
    é»Ħç´ł
    -0.06
    åŃ¦ä¹łæķĪçİĩ
    -0.06
    ously
    -0.06
    KeyId
    -0.06
    dling
    -0.06
    ally
    -0.06
    ä¸į足ä¹ĭå¤Ħ
    -0.06
     Destructor
    -0.06
     dah
    -0.05
    POSITIVE LOGITS
    élite
    0.09
    æĹ¥ä»¥
    0.09
    .um
    0.08
    å±ħåīį
    0.08
    :list
    0.08
     vá»±c
    0.08
    ä»»ä½ķä¿Ŀè¯ģ
    0.08
    -names
    0.08
    èĤĮ
    0.07
    ×ķ׼׾
    0.07
    Activations Density 0.027%

    No Known Activations