© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48571
    Prev
    Next
    INDEX
    Explanations

    is always/also/well/necessary/possible

    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
     оÑĤÑĤ
    -0.07
     quê
    -0.07
    ستاÙĨ
    -0.07
    ãģIJ
    -0.07
    erek
    -0.07
    _decoder
    -0.07
    orem
    -0.07
    ÑģÑĤоÑĢо
    -0.07
    rast
    -0.07
    oren
    -0.06
    POSITIVE LOGITS
     raining
    0.09
     bahwa
    0.08
     faptul
    0.08
     clear
    0.08
     bahawa
    0.07
     vorba
    0.07
    iner
    0.07
    éĩįè¦ģçļĦæĺ¯
    0.07
     customary
    0.07
     prudent
    0.07
    Activations Density 0.588%

    No Known Activations