© 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. 46415
    Prev
    Next
    INDEX
    Explanations

    diminished or ended state

    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
    æīĢæľīçļĦ
    -0.09
    æīĢæľī
    -0.08
    trato
    -0.07
    leman
    -0.07
    æĺ¯æīĢæľī
    -0.07
    anje
    -0.07
    cession
    -0.07
    bose
    -0.07
    ãĤı
    -0.07
    æĺ¯äººçĶŁ
    -0.07
    POSITIVE LOGITS
    iano
    0.07
    ous
    0.07
    æľįåĬ¡ä¼ģä¸ļ
    0.07
    lak
    0.06
    éĨĭ
    0.06
    çļĦæŶåĢĻå°±
    0.06
     prer
    0.06
    abilia
    0.06
     Gul
    0.06
    çļ®çļĦ
    0.06
    Activations Density 0.154%

    No Known Activations