© 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. 11648
    Prev
    Next
    INDEX
    Explanations

    positron-emitting radioligands

    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
     outright
    -0.07
    rav
    -0.07
    è°ĭ
    -0.07
    redi
    -0.07
    çĶ¨äºİ
    -0.07
     strang
    -0.07
    æĬķèµĦæĪĸæݧèĤ¡
    -0.06
     Humph
    -0.06
    guh
    -0.06
    zier
    -0.06
    POSITIVE LOGITS
    çļĦä¸įæĸŃ
    0.07
    çļĦ確
    0.07
    éĩĬæĶ¾åĩº
    0.07
    ï¸İ
    0.07
    isks
    0.07
    ):\
    0.07
    artos
    0.06
    cka
    0.06
    羣çļĦæľī
    0.06
    _bindings
    0.06
    Activations Density 0.018%

    No Known Activations