© 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. 58212
    Prev
    Next
    INDEX
    Explanations

    division results followed by numbers or operators

    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
    ัà¸ĩ
    -0.08
    ÙĪرÛĮ
    -0.08
    gow
    -0.07
    åĵ
    -0.07
     insomma
    -0.07
    !("{
    -0.07
    åĶ§
    -0.07
    ิà¹Īà¸ĩ
    -0.07
    ש×ķת
    -0.07
    è¿ĩå¤ļçļĦ
    -0.07
    POSITIVE LOGITS
    irik
    0.07
    aks
    0.07
    irit
    0.07
    åľºéĿ¢
    0.06
    arian
    0.06
    Ñħод
    0.06
    確ãģĭ
    0.06
     pup
    0.06
    esan
    0.06
    راض
    0.06
    Activations Density 0.006%

    No Known Activations