© 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. 11236
    Prev
    Next
    INDEX
    Explanations

    order and phase transitions

    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
     Gree
    -0.08
    æ¹ĥ
    -0.07
    àºŀ
    -0.07
    æĸ°çŁ¥
    -0.07
    éĥ
    -0.07
    ely
    -0.07
    åĽ¾åĨĮ
    -0.07
    eges
    -0.07
     seren
    -0.07
     Plaza
    -0.07
    POSITIVE LOGITS
    isu
    0.07
    天é¹ħ
    0.07
    å°¾
    0.07
    èijĨ
    0.07
    以为çĦ¶
    0.06
    çĭ¬æľīçļĦ
    0.06
    æĶ¿åºľåľ¨
    0.06
    lian
    0.06
     puro
    0.06
    å¸Ĥ缴
    0.06
    Activations Density 0.014%

    No Known Activations