© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18216
    Prev
    Next
    INDEX
    Explanations

    email alerts

    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
    ÑĬÑĤ
    -0.09
     //-
    -0.08
    imina
    -0.08
    ä¹ĭäºİ
    -0.07
    ä¹ĭ以
    -0.07
    ä¹ĭ为
    -0.07
    ä¸įäºĨçļĦ
    -0.07
    หà¸Ļึà¹Īà¸ĩà¸Ĺีà¹Ī
    -0.07
    lij
    -0.07
    iranya
    -0.07
    POSITIVE LOGITS
    æĽ´è¦ģ
    0.07
    ender
    0.07
    моÑģ
    0.07
    osos
    0.07
    asics
    0.07
     rather
    0.07
    enders
    0.06
    arana
    0.06
    be
    0.06
    aldas
    0.06
    Activations Density 0.321%

    No Known Activations