© 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. 65095
    Prev
    Next
    INDEX
    Explanations

    as/the/to followed by various words

    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
    arness
    -0.07
    äum
    -0.06
    Resolver
    -0.06
    æĹ
    -0.06
    stice
    -0.06
    ı
    -0.06
    olithic
    -0.06
    esan
    -0.06
    è°
    -0.06
    æĸĮ
    -0.06
    POSITIVE LOGITS
     also
    0.08
    also
    0.08
    hô
    0.08
    beau
    0.08
     moreover
    0.08
     examples
    0.07
    ä¸İåĽ½å®¶
    0.07
    å¯¹åĽ½å®¶
    0.07
     ÑĤакже
    0.07
    ä»»ä½ķåħ¶ä»ĸ
    0.07
    Activations Density 0.430%

    No Known Activations