© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15197
    Prev
    Next
    INDEX
    Explanations

    the followed by a word

    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
    è
    -0.07
    ä¸įæĭĶ
    -0.06
    æĭĶ
    -0.06
    æĢħ
    -0.06
    å±ħçĦ¶æĺ¯
    -0.06
    æĩ¿
    -0.06
     randomness
    -0.06
     pat
    -0.06
     anonymity
    -0.06
    ä¸įå¤ļçļĦ
    -0.06
    POSITIVE LOGITS
    ses
    0.09
    aget
    0.08
     langues
    0.08
    unts
    0.07
    æŀģ管
    0.07
     geschie
    0.07
    伯çī¹
    0.07
    èĢĥè¯ķç½ij
    0.07
    isin
    0.07
    osoph
    0.07
    Activations Density 1.162%

    No Known Activations