© 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. 14729
    Prev
    Next
    INDEX
    Explanations

    2x or 2y

    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
    iben
    -0.07
    leven
    -0.07
    кÑĥлÑıÑĢ
    -0.07
    inie
    -0.07
    éķ¿éķ¿
    -0.07
    etto
    -0.07
    anke
    -0.07
    Ñģмо
    -0.07
    åĴª
    -0.07
     chains
    -0.07
    POSITIVE LOGITS
    åĢįçļĦ
    0.07
    cpy
    0.07
    nowledge
    0.07
    trand
    0.07
    以åīįçļĦ
    0.07
    oppable
    0.07
    ä¸Ģ次çļĦ
    0.06
    ¬´
    0.06
    POINT
    0.06
    éĦĻ
    0.06
    Activations Density 0.005%

    No Known Activations