© 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. 48854
    Prev
    Next
    INDEX
    Explanations

    ranges and intervals

    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
    äºĶ次
    -0.07
    å¤ĸäºĭ
    -0.07
    iak
    -0.07
    äºĭåħĪ
    -0.07
    à¹ĥà¸Ļà¸ķัว
    -0.07
    imba
    -0.07
    ä¸Ĭæ·»
    -0.07
    anty
    -0.07
     conditioned
    -0.07
    æĿijæĿijæ°ij
    -0.07
    POSITIVE LOGITS
    çķĮå®ļ
    0.09
     defines
    0.09
    绣称
    0.08
    èĮĥåĽ´
    0.08
    å®ļä¹īäºĨ
    0.08
    defines
    0.08
     ranges
    0.08
     define
    0.08
    ndef
    0.08
    .define
    0.08
    Activations Density 0.024%

    No Known Activations