© 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. 46014
    Prev
    Next
    INDEX
    Explanations

    `math` or `variable`

    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
     later
    -0.07
    apar
    -0.06
    .same
    -0.06
    -0.06
    å½¢
    -0.06
    å°
    -0.06
     B
    -0.06
    çĻ¾
    -0.06
     F
    -0.05
     midd
    -0.05
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.09
    먼
    0.08
    ναν
    0.08
    é¦ĸåħĪè¦ģ
    0.08
    ä»Ģä¹Īåij¢
    0.08
    夫æĸ¯åŁº
    0.08
    é¦ĸåħĪåľ¨
    0.08
    нави
    0.08
    å§Ĩæĸ¯
    0.08
    ãĤĵãģ°ãĤĵ
    0.08
    Activations Density 0.333%

    No Known Activations