© 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. 34518
    Prev
    Next
    INDEX
    Explanations

    incorporates or Inherits

    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
    Thrown
    -0.08
    éĻ
    -0.07
    çľ¼çĿģçĿģ
    -0.07
    uhe
    -0.07
    uple
    -0.06
    ntag
    -0.06
    æŃ£å¸¸æĥħåĨµä¸ĭ
    -0.06
    undry
    -0.06
    糸
    -0.06
    agni
    -0.06
    POSITIVE LOGITS
     incorporates
    0.10
     Incorpor
    0.09
    åĢŁéī´
    0.09
     incorpora
    0.08
    ä¹ŁåıĹåĪ°
    0.08
     inherits
    0.08
     incorporate
    0.08
     Inherits
    0.08
     homage
    0.08
    继æī¿äºĨ
    0.08
    Activations Density 0.143%

    No Known Activations