© 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. 17230
    Prev
    Next
    INDEX
    Explanations

    second stage

    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
    indir
    -0.07
    ãģĭãĤı
    -0.07
    estring
    -0.07
    è¦ģæ±ĤåIJĦ
    -0.07
     kese
    -0.07
    igin
    -0.06
    ainless
    -0.06
    ä¹ĭæķ°
    -0.06
    æѦåĬĽ
    -0.06
    IGIN
    -0.06
    POSITIVE LOGITS
    ä¸įåĪ°
    0.07
     till
    0.07
    è¥
    0.07
    ård
    0.07
    å»ł
    0.07
    _PI
    0.07
    è´ŁçļĦ
    0.07
    ä¹ī
    0.07
    graphs
    0.07
    _PO
    0.07
    Activations Density 0.003%

    No Known Activations