© 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. 61416
    Prev
    Next
    INDEX
    Explanations

    diverse, molecular, lattice matched

    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
    ç¾İä¸Ń
    -0.07
    aur
    -0.07
    icies
    -0.07
    è¿ħ鼷
    -0.07
    æ¡Īä¸Ń
    -0.07
    çĭ¬æľī
    -0.07
    ä¸įåIJĮè§Ĵ度
    -0.07
    å²ģäºĨ
    -0.07
    olla
    -0.06
    æīĢä½ľ
    -0.06
    POSITIVE LOGITS
    为ä¸Ģä½ĵçļĦ
    0.10
    大äºİ
    0.09
    åľ¨åĨħçļĦ
    0.09
    æľīä¸Ģå®ļ
    0.09
    ìĹĨëĬĶ
    0.08
    ãģ®ãģªãģĦ
    0.08
    为主é¢ĺçļĦ
    0.08
    åı·ä¸º
    0.08
    è¾ĥ为
    0.07
    çĽ¸å¯¹
    0.07
    Activations Density 0.032%

    No Known Activations