© 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. 61796
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in programming contexts

    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
    åħ»
    -0.08
    æĮĩæŃ£
    -0.06
    me
    -0.06
    enary
    -0.06
    zag
    -0.06
    è´¼
    -0.06
     Me
    -0.06
    gem
    -0.06
    æĸ¹éĿ¢
    -0.06
    bel
    -0.06
    POSITIVE LOGITS
    again
    0.10
     again
    0.09
     Again
    0.09
    Again
    0.08
    icarbon
    0.08
    roh
    0.08
    æ¸ī
    0.08
     опÑıÑĤÑĮ
    0.08
    çªŁ
    0.08
    iliar
    0.08
    Activations Density 0.023%

    No Known Activations