© 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. 49860
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and cases

    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
    athan
    -0.07
    ight
    -0.07
    pery
    -0.07
    da
    -0.07
    ublic
    -0.07
    ase
    -0.07
    ä¹Łæĺ¯
    -0.07
    åĴĮä½ľçĶ¨
    -0.07
    enth
    -0.07
    åĴĮ
    -0.07
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.10
    eiro
    0.09
    elet
    0.08
    ebr
    0.08
    æ¯Ľæ³½ä¸ľ
    0.07
    eira
    0.07
    hern
    0.07
    ofday
    0.07
    æĸ°åĬłåĿ¡
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    Activations Density 0.005%

    No Known Activations