© 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. 16765
    Prev
    Next
    INDEX
    Explanations

    examines the

    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
    iloc
    -0.07
    ivot
    -0.07
    æī¶
    -0.07
    æĭ¯
    -0.07
    让å®ĥ们
    -0.07
    neo
    -0.06
    éħĮ
    -0.06
    让åħ¶
    -0.06
    arat
    -0.06
    污
    -0.06
    POSITIVE LOGITS
     titled
    0.08
    èŃĺ
    0.07
    xdc
    0.07
    èµ°è¿ij
    0.07
    槻
    0.07
    æĥij
    0.07
    alh
    0.07
    atlan
    0.07
     Äijâu
    0.07
    认è¯ĨçļĦ
    0.07
    Activations Density 0.016%

    No Known Activations