© 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. 62345
    Prev
    Next
    INDEX
    Explanations

    interference or background noise

    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
    èģĶç³»
    -0.07
     Versailles
    -0.07
     change
    -0.07
    communic
    -0.07
     deepen
    -0.07
     Change
    -0.07
    γή
    -0.06
    change
    -0.06
    è§ĦèĮĥæĢ§
    -0.06
    mlin
    -0.06
    POSITIVE LOGITS
    å¹²æī°
    0.13
    å¹²æĵ¾
    0.12
     interference
    0.11
     interfering
    0.11
    èĥĮæĻ¯
    0.10
    éģ®èĶ½
    0.10
    /background
    0.09
    æĿĤ
    0.09
     interfere
    0.09
    undi
    0.09
    Activations Density 0.089%

    No Known Activations