© 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. 56072
    Prev
    Next
    INDEX
    Explanations

    time units (seconds, hours, minutes)

    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
    ameda
    -0.08
    iller
    -0.08
    alles
    -0.08
    æŀī
    -0.08
    kah
    -0.08
    ëħIJ
    -0.07
    	typ
    -0.07
    дав
    -0.07
    建çļĦ
    -0.07
    onnier
    -0.07
    POSITIVE LOGITS
    жай
    0.07
     hourly
    0.06
    å°ıæŶ
    0.06
     Ven
    0.06
    äºľ
    0.06
    åħ³èĬĤ
    0.06
     icing
    0.06
    Hour
    0.06
    çļĦèĩªçĶ±
    0.06
     day
    0.05
    Activations Density 0.008%

    No Known Activations