© 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. 10391
    Prev
    Next
    INDEX
    Explanations

    gyroscopic effect, repulsion, invariant measure, pdf, formula, notation, materials

    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
    åħµå½¹
    -0.07
    ä¸ĥéĩĮ
    -0.07
    ohan
    -0.07
    ç©
    -0.06
    semb
    -0.06
    oke
    -0.06
    ãģ³
    -0.06
    éĩİçĮª
    -0.06
    ç¦ıæĺŁ
    -0.06
    éľ
    -0.06
    POSITIVE LOGITS
    åĬĿ
    0.08
    çĨŁçŁ¥
    0.08
    ç½¹æĤ£
    0.07
    çĨŁçŁ¥çļĦ
    0.07
    å°ĨæĮīçħ§
    0.07
    åĬ£
    0.07
    _skb
    0.07
    Requires
    0.07
    çĨŁ
    0.07
    uille
    0.07
    Activations Density 0.018%

    No Known Activations