© 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. 39934
    Prev
    Next
    INDEX
    Explanations

    marker of abnormal sign

    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
    Ãłng
    -0.07
     mele
    -0.07
    æł¹æľ¬å°±æ²¡æľī
    -0.06
    azit
    -0.06
    ut
    -0.06
    bas
    -0.06
    æ°´åĮº
    -0.06
     realities
    -0.06
    çĹħéŃĶ
    -0.06
    everything
    -0.06
    POSITIVE LOGITS
    é¢Ħ示çĿĢ
    0.12
    å¤ļè§ģäºİ
    0.11
    çļĦåĩºçİ°
    0.11
     Indicates
    0.11
     ominous
    0.11
     Ñģигнали
    0.10
    é¢Ħ示
    0.10
     indicates
    0.10
     abnormal
    0.10
     signifies
    0.10
    Activations Density 0.078%

    No Known Activations