© 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. 64997
    Prev
    Next
    INDEX
    Explanations

    younger grads

    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
    äºĴæį¢
    -0.09
     opposing
    -0.09
     ë°ĺëĮĢ
    -0.09
    åıĮåIJij
    -0.08
     opposite
    -0.08
     oppos
    -0.08
    åıĮæĸ¹
    -0.08
     swap
    -0.08
    .swap
    -0.08
    è¾±
    -0.08
    POSITIVE LOGITS
    éĢIJ级
    0.14
    å±Ĥå±Ĥ
    0.12
     progressively
    0.12
    ä¸ī级
    0.11
    å±Ĥ次
    0.11
    å±Ĥ级
    0.11
    éĢĴ
    0.10
    两级
    0.10
     hierarchy
    0.10
     tier
    0.10
    Activations Density 0.097%

    No Known Activations