© 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. 39466
    Prev
    Next
    INDEX
    Explanations

    negative numbers

    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
    INCT
    -0.09
    allet
    -0.08
    vence
    -0.08
    irro
    -0.08
    ạch
    -0.07
    ç¿İ
    -0.07
    [l
    -0.07
    å¾ħåĪ°
    -0.07
    çĵ¦å°Ķ
    -0.07
    estan
    -0.07
    POSITIVE LOGITS
    æ°´
    0.07
    ÙĬات
    0.07
    大åIJį
    0.06
    اÙĥ
    0.06
    åIJ»
    0.06
    yin
    0.06
    rone
    0.06
    åıį
    0.06
    ron
    0.06
    xis
    0.06
    Activations Density 0.043%

    No Known Activations