© 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. 18739
    Prev
    Next
    INDEX
    Explanations

    register keyword

    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
    êµ´
    -0.09
    Ñĭл
    -0.08
    IRD
    -0.08
    å°ĸ
    -0.08
    oghi
    -0.08
    以ä¸ĭåĩłçĤ¹
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    IGNORE
    -0.07
     milan
    -0.07
    è¯ĿæĿ¥
    -0.07
    POSITIVE LOGITS
    åij½åIJį为
    0.07
     dabei
    0.06
    åIJİèĢħ
    0.06
    obre
    0.06
    obo
    0.06
     known
    0.06
     latter
    0.06
     flat
    0.06
    วาส
    0.06
    åĬłåĭĴ
    0.06
    Activations Density 0.010%

    No Known Activations