© 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. 43336
    Prev
    Next
    INDEX
    Explanations

    date and time expressions

    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
    oftware
    -0.10
    Ĥ
    -0.10
    د
    -0.10
    er
    -0.09
    eries
    -0.09
    Ø©
    -0.09
    ÑģÑı
    -0.09
    quilla
    -0.09
    hips
    -0.09
    داب
    -0.09
    POSITIVE LOGITS
    ä¸īé¤IJ
    0.08
    çĤİçĤİ
    0.08
    avenport
    0.08
    å§ĭèĩ³ç»Ī
    0.08
    ä½ķåľ°
    0.07
    sh
    0.07
    inalg
    0.07
    untut
    0.07
    ´
    0.07
    à¸Ĥà¹Īาวสาร
    0.07
    Activations Density 0.007%

    No Known Activations