© 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. 23549
    Prev
    Next
    INDEX
    Explanations

    /private keys or max number

    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
    agraph
    -0.08
    è¿Ļ个女人
    -0.07
    endio
    -0.07
    رÙĬدة
    -0.07
    -time
    -0.07
    iores
    -0.07
    urang
    -0.07
    enov
    -0.06
    ä¸īäºĶ
    -0.06
    ÑĥÑħ
    -0.06
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.08
    åıĬ对
    0.07
    å¾Ĺå½ĵ
    0.07
    以åıĬ对
    0.07
    worth
    0.07
     dich
    0.07
    asel
    0.07
    ä¹ĭåĪĨ
    0.06
    Ń
    0.06
    对称
    0.06
    Activations Density 0.028%

    No Known Activations