© 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. 18217
    Prev
    Next
    INDEX
    Explanations

    cytosolic [Ca2+]i

    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
    åħ¶å¯¹
    -0.08
    _iff
    -0.07
    orz
    -0.07
    ansa
    -0.07
    áĢĤ
    -0.07
    angka
    -0.07
    åħīæĺİçļĦ
    -0.07
    èĪµ
    -0.07
    adge
    -0.06
    resp
    -0.06
    POSITIVE LOGITS
    gebra
    0.07
    ysi
    0.07
    euw
    0.07
    ambe
    0.07
    ©
    0.07
    _LOADED
    0.07
    çĦī
    0.07
    ovu
    0.07
    istan
    0.07
    ä¸Ģ缮
    0.07
    Activations Density 0.002%

    No Known Activations