© 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. 8823
    Prev
    Next
    INDEX
    Explanations

    summary contents

    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
    -0.08
    erede
    -0.07
    ereum
    -0.07
    åİĤçļĦ
    -0.07
    éħ¸çĶľèĭ¦è¾£
    -0.07
    å¥Īä½ķ
    -0.07
    edeut
    -0.07
    enticator
    -0.07
    å¦ĤçĥŁ
    -0.07
    ried
    -0.07
    POSITIVE LOGITS
    voud
    0.08
    æĸ°åĬłåĿ¡
    0.08
    uah
    0.07
    æĻĸ
    0.07
    è¹Ī
    0.07
    çħĮ
    0.07
    BAS
    0.07
    ucher
    0.07
    Bas
    0.07
    tring
    0.07
    Activations Density 0.006%

    No Known Activations