© 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. 51516
    Prev
    Next
    INDEX
    Explanations

    nuclear structure, physics, medicine, receptors, magnetic

    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
    amax
    -0.09
    ibs
    -0.08
    ewire
    -0.08
    tings
    -0.08
    /*@
    -0.08
    à§įত
    -0.08
    éĩijéĴ±
    -0.08
    èĽī
    -0.08
    llib
    -0.08
     volna
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¿åºľ
    0.07
    å´©
    0.07
    ered
    0.07
    /ne
    0.07
     nuclear
    0.07
     atomic
    0.06
     frat
    0.06
    -level
    0.06
     recoil
    0.06
     parl
    0.06
    Activations Density 0.007%

    No Known Activations