© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions ending parenthesis

    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
    ÑĨеÑĢ
    -0.07
    讨
    -0.07
    azel
    -0.07
    ity
    -0.07
    &A
    -0.07
     *&
    -0.07
    اتÙĬ
    -0.06
     Blasio
    -0.06
    atif
    -0.06
    -Star
    -0.06
    POSITIVE LOGITS
    HW
    0.07
    CHIP
    0.07
    acho
    0.07
    éĢ®
    0.07
    ÄĹj
    0.07
    æī¾äºº
    0.06
     IDD
    0.06
    æİĪ
    0.06
    çĪ±æĪij
    0.06
    irin
    0.06
    Activations Density 0.018%

    No Known Activations