© 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. 19266
    Prev
    Next
    INDEX
    Explanations

    military and religious titles

    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
     Baghd
    -0.09
    aldi
    -0.08
    ópolis
    -0.08
    ä¹ĭ主
    -0.08
    é¦ĸ缸
    -0.08
    ansch
    -0.08
    oroz
    -0.08
    ovac
    -0.08
    okon
    -0.08
    Oi
    -0.07
    POSITIVE LOGITS
    ä»»
    0.07
     D
    0.06
    们éĥ½
    0.06
    ÑĤÑİ
    0.06
     Emer
    0.06
    ('.'
    0.06
     M
    0.06
     A
    0.06
     d
    0.06
    人
    0.06
    Activations Density 0.245%

    No Known Activations