© 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. 46811
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a comma

    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
    áĥļáĥIJ
    -0.07
    å°±è¿Ļä¹Ī
    -0.06
     quarter
    -0.06
    {/
    -0.06
     +"
    -0.06
    ys
    -0.06
    onat
    -0.06
    ä½Ĩèĭ¥
    -0.06
    "..
    -0.06
    ÙĦز
    -0.06
    POSITIVE LOGITS
    å°Ħ
    0.07
    hani
    0.07
     Ngũ
    0.07
    .Sn
    0.07
    æī¦
    0.07
     Ñģно
    0.07
    æ·±åħ¥äºĨ解
    0.07
    ipes
    0.07
    çŁ³æŀĹ
    0.07
    blr
    0.07
    Activations Density 0.085%

    No Known Activations