© 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. 33658
    Prev
    Next
    INDEX
    Explanations

    numbers between 0 and 7

    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
     Einst
    -0.08
    eges
    -0.07
    __))
    -0.07
    -turned
    -0.07
    _mt
    -0.07
    åIJĮä»ģ
    -0.07
    å¥½å·¥ä½ľ
    -0.07
    å¤ļåĽ¾
    -0.07
    leih
    -0.07
    ayah
    -0.07
    POSITIVE LOGITS
     inclusive
    0.09
    ãģĦãģļãĤĮ
    0.09
    åĪĨåĪ«
    0.08
    åĨįåĪ°
    0.08
     inclusiv
    0.08
    ¹
    0.07
     jeweils
    0.07
    ãģ«ãģĭãģijãģ¦
    0.07
     respectively
    0.07
     гг
    0.07
    Activations Density 0.016%

    No Known Activations