© 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. 61295
    Prev
    Next
    INDEX
    Explanations

    practice verbs

    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
    alz
    -0.09
    æ¶īäºĭ
    -0.08
    escu
    -0.08
    wenc
    -0.08
    azard
    -0.08
    кок
    -0.08
    heed
    -0.08
    å¿ĥæľī
    -0.08
    人士
    -0.08
    colar
    -0.08
    POSITIVE LOGITS
     principles
    0.08
    ä½ĵçİ°
    0.07
    çīĪçļĦ
    0.07
    åħ¶è§ĤçĤ¹
    0.07
    è¿Ļä¸Ģ
    0.07
    uate
    0.07
     inherited
    0.07
    èĩªå·±çļĦæĥ³æ³ķ
    0.07
    表çİ°åĩºæĿ¥
    0.07
     пÑĢинÑĨи
    0.07
    Activations Density 0.301%

    No Known Activations