© 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. 25575
    Prev
    Next
    INDEX
    Explanations

    describing characteristics or definitions

    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
     nhau
    -0.08
    éĻĽ
    -0.07
    åIJĪçī©
    -0.07
    (?)
    -0.07
    ä¸īå°º
    -0.07
    /black
    -0.06
    -worthy
    -0.06
    æ¬Ĭ
    -0.06
    udging
    -0.06
    çĶ°
    -0.06
    POSITIVE LOGITS
    çī¹çĤ¹
    0.10
    çī¹çĤ¹æĺ¯
    0.10
     itib
    0.10
    çī¹çĤ¹åĴĮ
    0.10
    åĴĮå·¥ä½ľ
    0.10
    åĴĮ使çĶ¨
    0.09
    åĴĮçī¹çĤ¹
    0.09
    åĴĮæĵįä½ľ
    0.09
    åĴĮçĶŁæ´»
    0.08
    rip
    0.08
    Activations Density 0.201%

    No Known Activations