© 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. 24094
    Prev
    Next
    INDEX
    Explanations

    changes with replacement level

    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
    ENDA
    -0.08
    ulti
    -0.08
    haber
    -0.08
    åıĬæĹ¶è§£åĨ³
    -0.08
    SError
    -0.08
    ysi
    -0.08
    usus
    -0.08
    reu
    -0.08
    INTR
    -0.07
    NotificationCenter
    -0.07
    POSITIVE LOGITS
     본격
    0.08
     meaningful
    0.08
    并å¼Ģå§ĭ
    0.08
    å¼Ģå§ĭåĩºçİ°
    0.08
    å¼Ģå§ĭåľ¨
    0.08
    å¼Ģå§ĭ
    0.07
     Lloyd
    0.07
    被认为æĺ¯
    0.07
    meaning
    0.06
    ä¹Łå°±æĺ¯è¯´
    0.06
    Activations Density 0.093%

    No Known Activations