© 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. 8832
    Prev
    Next
    INDEX
    Explanations

    code blocks ending in } Z

    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
    erat
    -0.08
    å¯ĦçĶŁ
    -0.08
    ariat
    -0.07
    èº
    -0.07
     xem
    -0.07
    :event
    -0.07
    nod
    -0.07
    Watch
    -0.07
    orthand
    -0.07
    :not
    -0.07
    POSITIVE LOGITS
    ç§įç§į
    0.08
    çŃīçŃī
    0.07
    åħ·ä½ĵéĹ®é¢ĺ
    0.07
    ermal
    0.07
    翼翼
    0.07
    eries
    0.06
    æĿijæĿijæ°ij
    0.06
    诸
    0.06
    odel
    0.06
     Responsibilities
    0.06
    Activations Density 0.077%

    No Known Activations