© 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. 62744
    Prev
    Next
    INDEX
    Explanations

    quantitative calculation estimation

    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
     entirety
    -0.08
    Ø«ÙĨ
    -0.07
     integrity
    -0.07
     willingly
    -0.07
    omat
    -0.07
    allel
    -0.07
    åĶ¯ä¸ĢçļĦ
    -0.07
    æīĢæľīçļĦ人
    -0.07
     distra
    -0.07
    åħ¨éĥ¨çļĦ
    -0.07
    POSITIVE LOGITS
    ä¼°ç®Ĺ
    0.14
     estimates
    0.14
     estimate
    0.13
     realistic
    0.12
     estimated
    0.11
     Estimates
    0.11
     Estimate
    0.11
     calculations
    0.11
    estimate
    0.11
    æµĭç®Ĺ
    0.10
    Activations Density 0.023%

    No Known Activations