© 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. 51148
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and ideas

    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
    æ¥ļæ¥ļ
    -0.07
    statt
    -0.07
    chter
    -0.07
    çĹĬ
    -0.07
    ymoon
    -0.07
    weg
    -0.07
    ä¸ĢæľĿ
    -0.07
    .Concurrent
    -0.07
    æŁ±
    -0.07
    ensis
    -0.07
    POSITIVE LOGITS
    æĹłå¤Ħä¸įåľ¨
    0.11
    è¿Ļä¸ľè¥¿
    0.09
    çļĦå®ļä¹ī
    0.08
    对äºİæĪij们
    0.08
    广ä¹ī
    0.08
    ä¸Ģè¯į
    0.08
    ä¹ĭäºİ
    0.08
    åı¯åĪĨ为
    0.08
    ä¸ĩèĥ½
    0.08
     everywhere
    0.08
    Activations Density 0.465%

    No Known Activations