© 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. 16403
    Prev
    Next
    INDEX
    Explanations

    APPEALS OR TEXAS

    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
    好ä¸į
    -0.08
    باش
    -0.08
     Ante
    -0.08
    ×¥
    -0.07
    éĩįè¦ģçļĦäºĭæĥħ
    -0.07
    anteed
    -0.07
    arat
    -0.07
    -0.07
    åħ·å¤ĩèī¯å¥½çļĦ
    -0.07
    صد
    -0.07
    POSITIVE LOGITS
    å±±ä¹ĭ
    0.07
    山大
    0.07
    å±±çļĦ
    0.07
     es
    0.06
    سÙĬ
    0.06
    è¾¹çļĦ
    0.06
    ellä
    0.06
    اÙĨÙĬ
    0.06
    outs
    0.06
    ãĥĬãĤ¤
    0.06
    Activations Density 0.042%

    No Known Activations