© 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. 44055
    Prev
    Next
    INDEX
    Explanations

    counting words beginning with 't'

    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
    èIJ§
    -0.07
     Bru
    -0.06
    hill
    -0.06
    .gs
    -0.06
    enuity
    -0.06
    Bru
    -0.06
     gla
    -0.06
    mun
    -0.06
    éĤ£äºĽ
    -0.06
    ¦
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķä¸Ģç§į
    0.08
    utton
    0.08
    æ¯ıç§į
    0.07
     ÙħØ°
    0.07
    åħŃç§į
    0.07
    ä¸īç§į
    0.07
    addon
    0.07
    ove
    0.07
    æ¯ıä¸Ģç§į
    0.07
     kind
    0.07
    Activations Density 0.080%

    No Known Activations