© 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. 17507
    Prev
    Next
    INDEX
    Explanations

    two ways or routes

    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
    NotNull
    -0.08
     übrigens
    -0.07
    èİ·çĽĬ
    -0.07
    ToObject
    -0.07
     NYT
    -0.07
     concernés
    -0.06
    æľīè¿Ļæł·
    -0.06
    ascal
    -0.06
    æĹ¢åı¯
    -0.06
    ä¸įåıªæĺ¯
    -0.06
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.10
    å¹²èĦĨ
    0.10
    çŃīåħ¶ä»ĸ
    0.09
    ä»»ä½ķåħ¶ä»ĸ
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    æĽ´ä¸º
    0.08
    æł¹æľ¬å°±æĺ¯
    0.08
     ÑģобÑģÑĤвенно
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.08
    Activations Density 0.401%

    No Known Activations