© 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. 63898
    Prev
    Next
    INDEX
    Explanations

    shuttle, gate, Sports, connect

    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
    anser
    -0.08
    å¾Ĺè¿ĩ
    -0.07
    å¨Ľæ¨ĤåŁİ
    -0.07
    æ¬ł
    -0.06
    gars
    -0.06
    ãģĸ
    -0.06
    vole
    -0.06
    è¼
    -0.06
    å°ļ
    -0.06
    è®°
    -0.06
    POSITIVE LOGITS
    elu
    0.07
    /im
    0.07
    ظاÙĩ
    0.07
    å®Ļ
    0.07
    nik
    0.07
    _fx
    0.07
    åħ¶å®ĥ
    0.07
    tein
    0.07
    essoa
    0.06
    WND
    0.06
    Activations Density 0.066%

    No Known Activations