© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17730
    Prev
    Next
    INDEX
    Explanations

    electronic properties and electron transfer

    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
    åĺīå®ļ
    -0.07
    å½ĵ天
    -0.06
    itionally
    -0.06
    ourn
    -0.06
     duplicates
    -0.06
    جة
    -0.06
    ç½ijç«Ļåľ°åĽ¾
    -0.06
    æ·ĺæ±°
    -0.06
    ç§ij室
    -0.06
    åĪĹåħ¥
    -0.06
    POSITIVE LOGITS
    alit
    0.08
    inna
    0.08
    gra
    0.08
     neutrality
    0.07
    -rich
    0.07
     richness
    0.07
    å¹³åĿĩæ°´å¹³
    0.07
    adra
    0.07
    èĩªå·±è¢«
    0.07
    áĢ¬áĢ¸
    0.07
    Activations Density 0.004%

    No Known Activations