© 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. 50550
    Prev
    Next
    INDEX
    Explanations

    code blocks or delimiters

    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
    anei
    -0.08
     offsetof
    -0.08
    åĪĨéĴŁåīį
    -0.07
    edium
    -0.07
    uruh
    -0.07
    unger
    -0.07
    elingen
    -0.07
    #endregion
    -0.07
    iners
    -0.07
    à¹Ħà¸Ķà¹īà¸Ńย
    -0.07
    POSITIVE LOGITS
    sWith
    0.07
    0.06
    (/*
    0.06
    produce
    0.06
    ÙĨÙĬØ©
    0.06
    çĦ¶åIJİæĬĬ
    0.06
    asco
    0.06
    enced
    0.06
    åıĬè¦ģæ±Ĥ
    0.06
    cioni
    0.06
    Activations Density 0.023%

    No Known Activations