© 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. 33119
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
    ahoo
    -0.08
    å¥Īä½ķ
    -0.07
    noDB
    -0.07
    koz
    -0.07
    çī¹èģĺ
    -0.07
    liest
    -0.07
    uhan
    -0.07
    illah
    -0.07
    enteri
    -0.07
    SSION
    -0.06
    POSITIVE LOGITS
     truff
    0.07
    æ³ķåħ°åħĭç¦ı
    0.06
    vv
    0.06
    une
    0.06
    unist
    0.06
     cherry
    0.06
    è§Ĵ
    0.06
    以任ä½ķ
    0.06
    èv
    0.06
     dita
    0.06
    Activations Density 0.014%

    No Known Activations