© 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. 48547
    Prev
    Next
    INDEX
    Explanations

    possessive or contraction followed by abstract noun

    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
    onger
    -0.07
    zier
    -0.07
    èĴĻå¾·
    -0.07
    zis
    -0.07
    ucker
    -0.07
    æĦŁåħ´è¶£çļĦ
    -0.07
    ảng
    -0.06
    ç»ļçĥĤ
    -0.06
    åĽĽä¸ªæľĪ
    -0.06
     interested
    -0.06
    POSITIVE LOGITS
     role
    0.10
     ability
    0.09
    çļĦéĩįè¦ģæĢ§
    0.08
    ä½ľä¸º
    0.08
     importance
    0.08
     relevance
    0.08
     significance
    0.08
    æĮģãģ¤
    0.08
     suitability
    0.08
     reliance
    0.08
    Activations Density 0.242%

    No Known Activations