© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2718
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables

    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
    edin
    -0.09
    äºijéĽĨ
    -0.08
    Tac
    -0.07
    港åı°
    -0.07
    uben
    -0.07
    anus
    -0.06
    ä¹ħ
    -0.06
    å®ļãĤģ
    -0.06
    _PRED
    -0.06
    oute
    -0.06
    POSITIVE LOGITS
    æĪijçľĭè§ģ
    0.08
    ixer
    0.07
    çŁ³æŀĹ
    0.07
    è®°ä½ıäºĨ
    0.07
    بÙĪÙĦ
    0.07
    Creature
    0.07
    Holder
    0.07
    waran
    0.07
    FOUND
    0.07
    uit
    0.07
    Activations Density 0.020%

    No Known Activations