© 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. 58179
    Prev
    Next
    INDEX
    Explanations

    differential equations system coefficients

    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
    çĤ¹å¯¹
    -0.07
     mandat
    -0.06
    à¥įà¤Ł
    -0.06
    kens
    -0.06
    è¦ģæ±Ĥè¿Ľè¡Į
    -0.06
    esel
    -0.06
     kik
    -0.06
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸
    -0.06
    gest
    -0.06
    çŀ
    -0.06
    POSITIVE LOGITS
     evolves
    0.11
     evolve
    0.11
     dynamics
    0.10
     evolution
    0.09
     Dynamics
    0.09
     evolving
    0.09
    éļıçĿĢæŶéĹ´çļĦ
    0.09
     initialised
    0.09
     динами
    0.09
    rogram
    0.09
    Activations Density 0.028%

    No Known Activations