© 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. 18293
    Prev
    Next
    INDEX
    Explanations

    programmer, revision, requires

    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
     ute
    -0.07
    对çĻ½
    -0.07
    è¡·å¿ĥçļĦ
    -0.07
    วะ
    -0.07
    è¶ħéŁ³
    -0.07
    acción
    -0.07
    ç±»çŃī
    -0.06
    å¹´è¿Ī
    -0.06
    Probability
    -0.06
    çīĩçīĩ
    -0.06
    POSITIVE LOGITS
     pesc
    0.08
    丽ä¸Ŀ
    0.07
    anns
    0.07
    getPath
    0.07
    æ¡Ī
    0.07
    Ùħد
    0.07
    zier
    0.07
    ä¸įåĪ°çļĦ
    0.07
    ÙĨÙĪÙĨ
    0.06
     اÙĦتÙĨ
    0.06
    Activations Density 0.004%

    No Known Activations