© 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. 39352
    Prev
    Next
    INDEX
    Explanations

    correctness and validity

    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
    èµĦæĸĻä¸ĭè½½
    -0.08
    prus
    -0.08
    .override
    -0.08
    øl
    -0.08
    _decor
    -0.08
    lash
    -0.08
    çĶŁæ´»æĸ¹å¼ı
    -0.07
    adt
    -0.07
    æĪ
    -0.07
    æīĢæĭ¥æľīçļĦ
    -0.07
    POSITIVE LOGITS
     fit
    0.07
     isValid
    0.06
     fits
    0.06
     according
    0.06
    平衡
    0.06
    æŃ£ç»Ł
    0.06
    odes
    0.06
     balance
    0.06
    æŃ£ç¡®
    0.06
    he
    0.06
    Activations Density 0.125%

    No Known Activations