© 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. 1651
    Prev
    Next
    INDEX
    Explanations

    Akeeba Ltd

    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
    ada
    -0.07
    acc
    -0.07
    缩
    -0.07
    iba
    -0.07
    adas
    -0.06
    m
    -0.06
     acc
    -0.06
    趣åij³æĢ§
    -0.06
    人为
    -0.06
    acher
    -0.06
    POSITIVE LOGITS
    åĪ°äºĨä¸Ģ个
    0.08
    agus
    0.08
    åĭŁ
    0.07
    USTA
    0.07
    tua
    0.07
     (('
    0.07
    itia
    0.07
     *–
    0.07
    ihan
    0.07
    æł©
    0.07
    Activations Density 0.041%

    No Known Activations