© 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. 58137
    Prev
    Next
    INDEX
    Explanations

    algebraic relationships

    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
    麻麻
    -0.08
     ÙħرØŃ
    -0.08
    fahr
    -0.07
    LOGGER
    -0.07
    æľªåıĸå¾Ĺ
    -0.07
    æĬĺ
    -0.07
    shade
    -0.07
    éĤ£éģĵ
    -0.07
    urance
    -0.07
    ä¸Ģè¶Ł
    -0.07
    POSITIVE LOGITS
     relationships
    0.10
     governing
    0.09
     relations
    0.09
    relationships
    0.08
    åħ³ç³»
    0.08
    çĽ¸å®¹
    0.08
     relationship
    0.08
    çļĦä¸Ģç»Ħ
    0.08
     Relations
    0.08
    relations
    0.08
    Activations Density 0.006%

    No Known Activations