© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64419
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or words

    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
    claimer
    -0.09
    trut
    -0.08
    riture
    -0.08
    룸
    -0.08
    CONTEXT
    -0.08
    -kit
    -0.08
    æľŁä¸Ń
    -0.08
    rava
    -0.08
    æľºåħ³
    -0.07
    trup
    -0.07
    POSITIVE LOGITS
     remained
    0.07
     remaining
    0.07
    0.06
    åī©ä½ĻçļĦ
    0.06
     remains
    0.06
     experiences
    0.06
     uninsured
    0.06
     kalan
    0.06
     pik
    0.06
    OSE
    0.06
    Activations Density 0.049%

    No Known Activations