© 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. 38108
    Prev
    Next
    INDEX
    Explanations

    keypath observing

    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
    h
    -0.07
    orses
    -0.07
    iks
    -0.06
    綿
    -0.06
    hv
    -0.06
    ame
    -0.06
    orse
    -0.06
    سس
    -0.06
    mer
    -0.06
    поÑĢ
    -0.06
    POSITIVE LOGITS
    æIJIJ
    0.09
    ä»įçĦ¶
    0.08
    Ủ
    0.08
    committed
    0.08
    RLF
    0.08
    osting
    0.08
    è¿Ļä¸ĭ
    0.08
    okal
    0.08
    çİ°åľ¨å¼Ģå§ĭ
    0.08
     STILL
    0.07
    Activations Density 0.063%

    No Known Activations