© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62733
    Prev
    Next
    INDEX
    Explanations

    unpaired, random, set, long, movement, become, interact, dissemination, securely

    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
    adang
    -0.08
    ä¸Ģæ¯Ķ
    -0.08
    å¿ħé¡»åĿļæĮģ
    -0.08
    åĪ°ä¸Ģèµ·
    -0.08
    çĶĺäºİ
    -0.08
    两å¸Ĥ
    -0.08
    riture
    -0.07
    erlo
    -0.07
    anser
    -0.07
    饱åıĹ
    -0.07
    POSITIVE LOGITS
    uf
    0.08
    Âł
    0.06
    usz
    0.06
     “
    0.06
    º
    0.06
    gat
    0.06
    çĽĨ
    0.06
    åĬ¨åĬĽçļĦ
    0.06
    ino
    0.06
    å°¼äºļ
    0.06
    Activations Density 0.146%

    No Known Activations