© 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. 20093
    Prev
    Next
    INDEX
    Explanations

    direction and reverse

    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
    ettek
    -0.07
    åģļ人
    -0.07
    æĬĺ
    -0.07
    å¹»
    -0.07
    ([$
    -0.07
    _projection
    -0.07
    edit
    -0.07
    å¦Ĥæŀľèĥ½
    -0.07
    润泽
    -0.07
     przen
    -0.07
    POSITIVE LOGITS
    次åºı
    0.08
    éĢĨåIJij
    0.08
    顺åºı
    0.08
    éłĨåºı
    0.08
    çļĦ顺åºı
    0.08
    .reverse
    0.08
    Reverse
    0.07
    èľ¡
    0.07
    GBT
    0.07
    åĢĴéĢĢ
    0.07
    Activations Density 0.001%

    No Known Activations