© 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. 38774
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    WithContext
    -0.08
    evos
    -0.06
    à¸Ĺรà¹Į
    -0.06
    oyer
    -0.06
    ±
    -0.06
    udder
    -0.06
    ิà¸ĩ
    -0.06
    âĨĵâĨĵ
    -0.06
    µ
    -0.06
    羣çļĦ好
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.09
    缸è¾ħ缸æĪIJ
    0.08
    俱ä¹IJéĥ¨
    0.08
    åĬłæĭ¿å¤§
    0.07
    okane
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    壮
    0.07
    ä¹ĿäºĶ
    0.07
    andin
    0.07
    es
    0.07
    Activations Density 0.249%

    No Known Activations