© 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. 9209
    Prev
    Next
    INDEX
    Explanations

    primary colors, cyan, magenta, additive mixing

    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
    åħ·ä½ĵæŶéĹ´
    -0.07
    arque
    -0.07
    å¿ĥçİĩ
    -0.07
     migration
    -0.07
    migration
    -0.07
    è¿ģ
    -0.07
    æŶéĹ´èĬĤçĤ¹
    -0.07
    åħ¥åij³
    -0.06
    åıĮè¯Ń
    -0.06
     mot
    -0.06
    POSITIVE LOGITS
     combinations
    0.09
    èī²
    0.08
    èī²çļĦ
    0.08
    缸åĬł
    0.08
    ç»ĦåIJĪ
    0.08
    äºĴè¡¥
    0.08
     additive
    0.08
    缸åıįçļĦ
    0.08
    åĶ¯çĭ¬
    0.07
     Mixing
    0.07
    Activations Density 0.017%

    No Known Activations