© 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. 26770
    Prev
    Next
    INDEX
    Explanations

    URLs followed by links or media

    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
    chner
    -0.09
     íĥģ
    -0.08
    å¾ĹæĿ¥
    -0.08
    绣ä¸Ģå®īæİĴ
    -0.08
    ×ķ׳×Ķ
    -0.08
    íĥģ
    -0.08
    ationToken
    -0.07
    æŬ
    -0.07
     ë§
    -0.07
    ewise
    -0.07
    POSITIVE LOGITS
    å°Ķ
    0.06
    ailer
    0.06
    |
    0.06
    à¸Īริà¸ķ
    0.06
    滨æ¹ĸ
    0.06
    åĩºåĬ¨
    0.06
    ä¸į说
    0.06
    omad
    0.06
    çĽ
    0.05
    uck
    0.05
    Activations Density 0.001%

    No Known Activations