© 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. 45941
    Prev
    Next
    INDEX
    Explanations

    study types

    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
    åħ¶ä»ĸåªĴä½ĵ
    -0.09
    ÙĨب
    -0.09
    åľ¨åħĪ
    -0.08
    áĥĴáĥł
    -0.08
    åħ¶å®ĥåªĴä½ĵ
    -0.08
    onsin
    -0.08
    REFERRED
    -0.08
    æĽ´å¤ļåĨħ容
    -0.08
    æĸĩåĵ²
    -0.08
    赫çĦ¶
    -0.08
    POSITIVE LOGITS
    认为æĺ¯
    0.06
    ضÙħاÙħ
    0.06
     approach
    0.06
    以
    0.06
    0.06
    çľĭæ³ķ
    0.06
    èµ°è¿ij
    0.05
    æĿ¥èĩª
    0.05
     sequel
    0.05
    åħ³æ³¨
    0.05
    Activations Density 0.377%

    No Known Activations