© 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. 55753
    Prev
    Next
    INDEX
    Explanations

    describes what something is

    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
    olum
    -0.09
    quist
    -0.08
    ISTORY
    -0.08
    ä¿ĥåıijå±ķ
    -0.08
    mén
    -0.08
    ãĥ¬ãĥ³ãĥĢãĥ¼
    -0.08
    ove
    -0.08
    cept
    -0.08
    å®ĥ以
    -0.08
     dikat
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.10
    ä¸Ģç§į
    0.09
    ä»Ģä¹ĪæĦıæĢĿ
    0.09
    æŁIJç§į
    0.08
    ä»Ģä¹Īåij¢
    0.08
    ä¸Ģ種
    0.08
    ager
    0.08
    à¹Ħà¸Ķà¹ī
    0.07
     respectively
    0.07
    е
    0.07
    Activations Density 0.064%

    No Known Activations