© 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. 31569
    Prev
    Next
    INDEX
    Explanations

    Year of the Ages

    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
    åı£å¾Ħ
    -0.08
    åĴĨ
    -0.07
    ay
    -0.07
    vente
    -0.07
    aliste
    -0.07
    常è§ģéĹ®é¢ĺ
    -0.07
     \"{
    -0.07
    antas
    -0.07
    bullet
    -0.07
    æĢ§ä»·æ¯Ķ
    -0.07
    POSITIVE LOGITS
    对åºĶ
    0.12
     corresponds
    0.10
    对åºĶçļĦ
    0.09
     corresponding
    0.09
     correspond
    0.09
     Correspond
    0.09
    å°įæĩī
    0.09
    associated
    0.08
    çĽ¸å¯¹åºĶ
    0.08
     ÑģооÑĤвеÑĤÑģÑĤвенно
    0.08
    Activations Density 0.029%

    No Known Activations