© 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. 20829
    Prev
    Next
    INDEX
    Explanations

    introductions like "is the" or "are the"

    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
    cier
    -0.09
    ebo
    -0.08
    aos
    -0.08
    å®ĥ以
    -0.07
    _GRID
    -0.07
    å¦ĤæľŁ
    -0.07
    berman
    -0.07
    ாள
    -0.07
    ä¹ĭæ¯į
    -0.07
    sem
    -0.07
    POSITIVE LOGITS
    éĹ
    0.07
    úst
    0.07
    ag
    0.06
     repres
    0.06
    oral
    0.06
    kr
    0.06
    PR
    0.06
    hi
    0.06
    éĵ¶å±±
    0.06
    irc
    0.06
    Activations Density 0.001%

    No Known Activations