© 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. 21719
    Prev
    Next
    INDEX
    Explanations

    fluctuations and randomness

    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
    arif
    -0.08
    ä¸Ģè¶Ł
    -0.08
     simplific
    -0.08
    hone
    -0.08
    garten
    -0.07
    anzi
    -0.07
    anth
    -0.07
    κολ
    -0.07
    åıĬéĻĦåĬł
    -0.07
    à¹Īวà¸ĩ
    -0.07
    POSITIVE LOGITS
    èĩªåıij
    0.10
     spontaneous
    0.09
    涨
    0.09
    éļıæľº
    0.08
     random
    0.08
     spontaneously
    0.08
    ä¸įæķ£
    0.08
     fluctuations
    0.08
    random
    0.08
     spont
    0.07
    Activations Density 0.011%

    No Known Activations