© 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. 17873
    Prev
    Next
    INDEX
    Explanations

    asking this

    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
    lach
    -0.09
    dene
    -0.09
    è¯¥ä½ľèĢħ
    -0.08
    estina
    -0.08
    िल
    -0.08
    dete
    -0.08
    AccessException
    -0.08
    dze
    -0.08
    Å¡Äį
    -0.08
    xis
    -0.08
    POSITIVE LOGITS
    åħ³äºİ
    0.07
    åħ³äºİæĪij们
    0.07
    2
    0.06
    è¿Ļæł·ä¸Ģç§į
    0.06
    è¯Ĩ
    0.06
     about
    0.06
     specifically
    0.06
    how
    0.06
    ức
    0.06
     how
    0.06
    Activations Density 0.003%

    No Known Activations