© 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. 22769
    Prev
    Next
    INDEX
    Explanations

    if conditions

    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
    èĢĮ代ä¹ĭ
    -0.09
    åĪĻä¼ļ
    -0.08
    èĭ¥æĺ¯
    -0.08
    èĩ³æѤ
    -0.08
    ={$
    -0.08
    å¨Ĩ
    -0.08
    èĢĮè¨Ģ
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.08
    ones
    -0.07
     Mê
    -0.07
    POSITIVE LOGITS
    /how
    0.08
    ahr
    0.07
    the
    0.07
    :
    0.07
    ÙĬÙĨ
    0.07
    eland
    0.06
    ahre
    0.06
    ippy
    0.06
    ãģ£ãģĹãĤĥ
    0.06
    åĪ©çļĦ
    0.06
    Activations Density 0.051%

    No Known Activations