© 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. 16987
    Prev
    Next
    INDEX
    Explanations

    relativistic corrections

    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
    Ø´ÙĬ
    -0.08
    bsp
    -0.08
     Seger
    -0.08
    ä¸İæݧåĪ¶
    -0.07
    ä¹Ŀæ±Ł
    -0.07
     staged
    -0.07
    ständ
    -0.07
    inesi
    -0.07
    Brains
    -0.07
    bern
    -0.07
    POSITIVE LOGITS
     corrections
    0.09
    ä¿®æŃ£
    0.09
    éĵł
    0.08
     Corrections
    0.07
    ommer
    0.07
     correction
    0.07
    åĪĨå±Ģ
    0.07
     chrom
    0.07
     relativ
    0.07
    æĺ¯çĶ±äºİ
    0.06
    Activations Density 0.004%

    No Known Activations