© 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. 26098
    Prev
    Next
    INDEX
    Explanations

    Vatican, June, accounting, method

    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
    estina
    -0.07
     Caucus
    -0.07
    ofi
    -0.06
    ANIA
    -0.06
    åģļçļĦæĺ¯
    -0.06
    ecker
    -0.06
    åĢ¦
    -0.06
    交åĬŀ
    -0.06
    queo
    -0.06
     reference
    -0.06
    POSITIVE LOGITS
    wer
    0.07
    iede
    0.07
    æ½
    0.07
    	ext
    0.07
    åľ¨è§Ħå®ļ
    0.06
    enges
    0.06
    kie
    0.06
    менÑĤаÑĢ
    0.06
    Ground
    0.06
    ile
    0.06
    Activations Density 0.355%

    No Known Activations