© 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. 38697
    Prev
    Next
    INDEX
    Explanations

    details

    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
    est
    -0.07
    缸å½ĵ
    -0.07
    êµ°ìļĶ
    -0.06
    ige
    -0.06
    åĽłä¸ºæĺ¯
    -0.06
    ↵↵↵↵
    -0.06
    ä¸įåİ»
    -0.06
    ign
    -0.06
    ave
    -0.06
     Computing
    -0.06
    POSITIVE LOGITS
    erma
    0.08
    oÄį
    0.08
     Peker
    0.08
    íİ
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    ç¡ķæŀľ
    0.08
     ÑĢадÑĥ
    0.08
    åıªæľīèĩªå·±
    0.08
    èĩªå·±çļĦ身ä½ĵ
    0.08
    åħ¶ä¹IJ
    0.08
    Activations Density 0.001%

    No Known Activations