© 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. 24469
    Prev
    Next
    INDEX
    Explanations

    pull from stone, Jacob's ladder, Pied Piper, Wizard of Oz

    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
    å°Ķå¤ļ
    -0.08
    æĨ¬
    -0.08
    åĴĢ
    -0.07
    liner
    -0.07
    å°ıåŀĭ
    -0.07
    .Dispatcher
    -0.07
    _FA
    -0.07
    onge
    -0.06
     Justi
    -0.06
    Liv
    -0.06
    POSITIVE LOGITS
    è¿Ļ个æķħäºĭ
    0.09
    åħ¸æķħ
    0.09
    çļĦæķħäºĭ
    0.08
     minh
    0.08
    åħ¬è½¦
    0.08
     story
    0.08
    æ±īæѦå¸Ŀ
    0.07
     analogy
    0.07
    æĪIJè¯Ń
    0.07
    -story
    0.07
    Activations Density 0.002%

    No Known Activations