© 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. 48450
    Prev
    Next
    INDEX
    Explanations

    solve for variables

    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
    idak
    -0.07
    .defaults
    -0.07
    adis
    -0.07
    ewan
    -0.06
    èĪ¬
    -0.06
    kd
    -0.06
    大èĩªçĦ¶
    -0.06
    راجعة
    -0.06
    æĺ¥å¤ıç§ĭåĨ¬
    -0.06
    _into
    -0.06
    POSITIVE LOGITS
    è¿ĽèĢĮ
    0.08
    继èĢĮ
    0.08
    ç½ijç«Ļ导èĪª
    0.07
    æľªæŀľ
    0.07
     ÑģледÑĥÑİÑīим
    0.07
    åħ³ç³»åĪ°
    0.07
    >):
    0.07
    ammans
    0.07
    çĤ¹åĩ»åĽ¾çīĩ
    0.07
     }:
    0.07
    Activations Density 0.006%

    No Known Activations