© 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. 65303
    Prev
    Next
    INDEX
    Explanations

    prime number context

    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
    èĽĩ
    -0.07
    spin
    -0.06
    å¤ļ头
    -0.06
     Stag
    -0.06
    èĹķ
    -0.06
    çŁ¥å·±
    -0.06
    å¤ļç»´
    -0.06
    STACK
    -0.06
    ãĤ³ãĥ¢
    -0.06
    onz
    -0.06
    POSITIVE LOGITS
    endan
    0.08
    à¸ģว
    0.07
    angguan
    0.07
    ard
    0.07
    ummer
    0.07
    awah
    0.07
     fend
    0.07
    filer
    0.07
    onton
    0.07
    নà§įন
    0.07
    Activations Density 0.004%

    No Known Activations