© 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. 32076
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and calculations

    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
    éĻ
    -0.08
    /umd
    -0.07
    osto
    -0.06
    antasy
    -0.06
     voire
    -0.06
     [].
    -0.06
    annel
    -0.06
    ija
    -0.06
     اÙĦتدرÙĬ
    -0.06
    enity
    -0.06
    POSITIVE LOGITS
    gle
    0.08
    è´£ç¼ĸ
    0.07
    lee
    0.07
    iany
    0.07
    çİ°åľºç¡®è®¤
    0.07
    leitung
    0.07
     Synopsis
    0.07
    ldata
    0.07
    彪
    0.07
    atement
    0.07
    Activations Density 0.010%

    No Known Activations