© 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. 49273
    Prev
    Next
    INDEX
    Explanations

    dumpster rental, partial class, derivative of, asa rules, ash burn

    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
    åħ½
    -0.07
     dep
    -0.07
    ovie
    -0.06
     G
    -0.06
    -0.06
    ä¸Ģä¸Ģ
    -0.06
    绥
    -0.06
     g
    -0.06
     ther
    -0.06
    æѤå¤Ħ
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.09
    AYA
    0.08
    ADED
    0.08
    alom
    0.08
    addock
    0.08
    ç¥ŀä¹ĭ
    0.08
    entren
    0.08
    _proxy
    0.08
    PTY
    0.08
    ryn
    0.08
    Activations Density 0.005%

    No Known Activations