© 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. 31229
    Prev
    Next
    INDEX
    Explanations

    embedding or placing onto

    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
    utch
    -0.07
    èĢĮä½ľä¸º
    -0.07
    ARED
    -0.06
    綺
    -0.06
    为åĬłå¼º
    -0.06
    _nb
    -0.06
    ãĥŀãĥª
    -0.06
    ä»»ä½ķä¸Ģæĸ¹
    -0.06
    ä¸Ńå¿ĥå·¥ä½ľ
    -0.06
    Ø´ÙĪ
    -0.06
    POSITIVE LOGITS
     onto
    0.11
     ÑĤÑĥда
    0.11
     внÑĥÑĤÑĢÑĮ
    0.10
    onto
    0.10
    è¿Ľåİ»
    0.10
    ลà¸ĩà¹ĥà¸Ļ
    0.10
    Into
    0.10
    à¹Ģà¸Ĥà¹īาà¹Ħà¸Ľ
    0.10
    _into
    0.09
    éĢĤéĩıçļĦ
    0.09
    Activations Density 0.708%

    No Known Activations