© 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. 33355
    Prev
    Next
    INDEX
    Explanations

    a: followed by punctuation

    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
    åĬ²åĦ¿
    -0.08
    ä¸ĭæ°´
    -0.07
    waard
    -0.07
    å½ĵä¹ĭ
    -0.07
    çĤ¹åĦ¿
    -0.07
    èĶ
    -0.07
    epy
    -0.07
    phabet
    -0.07
    chema
    -0.07
    åŃĶéĽĢ
    -0.07
    POSITIVE LOGITS
     salut
    0.07
    cev
    0.06
    urred
    0.06
    ç²¾è¯ļ
    0.06
     radicale
    0.06
     responded
    0.06
    Ĺ
    0.06
    eron
    0.06
     رØŃ
    0.06
     dead
    0.06
    Activations Density 0.056%

    No Known Activations