© 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. 25794
    Prev
    Next
    INDEX
    Explanations

    If ABC : Functions ISO

    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
    ç£
    -0.07
    éĩijæĸ¯
    -0.07
    ones
    -0.07
    utate
    -0.07
    undes
    -0.06
    vana
    -0.06
    ä¹ĥèĩ³
    -0.06
     cất
    -0.06
    amet
    -0.06
    åħ¶äºĮ
    -0.06
    POSITIVE LOGITS
    ItemSelected
    0.07
    Ķ
    0.07
    æĬī
    0.07
    ĭ
    0.07
    çĿIJ
    0.07
    ))*
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    &T
    0.07
    !!!!!!!!
    0.07
    èī¾ä¼¦
    0.07
    Activations Density 0.002%

    No Known Activations