© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30420
    Prev
    Next
    INDEX
    Explanations

    ions, conductivity, K, H+ pumping

    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
    enho
    -0.08
    à¸Ĺà¸Ńà¸Ķ
    -0.08
    หัà¸ģ
    -0.08
    lott
    -0.07
    æ®ĥ
    -0.07
    etrics
    -0.07
    rauch
    -0.07
    etan
    -0.07
    èce
    -0.07
    èĬ±çº¹
    -0.07
    POSITIVE LOGITS
    /
    0.07
    åĪij
    0.06
    amburger
    0.06
    æµĵ度
    0.06
    /OR
    0.06
    æŁłæª¬
    0.06
    èĥĥ
    0.06
    oldt
    0.06
    -ion
    0.06
    athom
    0.06
    Activations Density 0.002%

    No Known Activations