© 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. 27196
    Prev
    Next
    INDEX
    Explanations

    implied or unspecified

    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
    å¹¿æ³ĽçĶ¨äºİ
    -0.08
    ucci
    -0.07
    ели
    -0.07
     typically
    -0.06
    çĭĻ
    -0.06
     yours
    -0.06
    绪
    -0.06
    æĪij们å§ĭç»Ī
    -0.06
    eyer
    -0.06
    å¹¿æ³ĽåºĶçĶ¨äºİ
    -0.06
    POSITIVE LOGITS
     evidently
    0.08
     offenbar
    0.08
     unnamed
    0.08
    åħ·ä½ĵçļĦ
    0.07
     apparently
    0.07
    临
    0.07
     implied
    0.07
    ä¸įè´¥
    0.07
     unspecified
    0.07
    åħľ
    0.07
    Activations Density 0.002%

    No Known Activations