© 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. 56659
    Prev
    Next
    INDEX
    Explanations

    named places in Ireland and Quebec

    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
    -0.07
    Ì
    -0.06
    åŁº
    -0.06
     lead
    -0.06
     effective
    -0.05
    ki
    -0.05
    èĮµ
    -0.05
     a
    -0.05
     *
    -0.05
    sem
    -0.05
    POSITIVE LOGITS
     wÅĤ
    0.09
    amaz
    0.09
    emergen
    0.08
    <|box_end|>
    0.08
    ë´
    0.08
    没帮åĬ©
    0.08
    åħ¨éĥ¨è¯Ħ论
    0.08
    itest
    0.08
    à¹īà¸Ńม
    0.08
    itosti
    0.08
    Activations Density 0.087%

    No Known Activations