© 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. 12368
    Prev
    Next
    INDEX
    Explanations

    nearby values or neighbors

    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
    ä¸Ģ度çļĦ
    -0.07
    åIJij社ä¼ļ
    -0.07
    çŃīåIJĦ项
    -0.07
    å·¥ä½ľè¦ģæ±Ĥ
    -0.07
    å®ĮæĪIJæĬķèµĦ
    -0.06
    porto
    -0.06
     getDescription
    -0.06
     nih
    -0.06
    åį¡ç½Ĺ
    -0.06
    ¬´
    -0.06
    POSITIVE LOGITS
    æ¯Ķèĩªå·±
    0.11
     nearby
    0.10
     neighboring
    0.09
    ä¸İèĩªå·±
    0.09
    åĴĮèĩªå·±
    0.09
     terdekat
    0.09
    éĤ»å±ħ
    0.08
    æ¯Ķä»ĸ
    0.08
    orthy
    0.08
     previous
    0.08
    Activations Density 0.040%

    No Known Activations