© 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. 49278
    Prev
    Next
    INDEX
    Explanations

    her followed by a name or title

    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
    aison
    -0.10
    eningen
    -0.08
    åĬ²åĦ¿
    -0.08
    eson
    -0.08
    ÙĦÙĬت
    -0.08
    غد
    -0.08
    ä¹ĭæģĭ
    -0.08
    yson
    -0.08
    ÛĮشاÙĨ
    -0.08
    åħļçļĦ建设
    -0.08
    POSITIVE LOGITS
    orary
    0.06
    导
    0.06
    one
    0.06
    éľĩ
    0.06
    ç¡ķ
    0.06
    åĩĨå¤ĩ好çļĦ
    0.05
    å¿ĥçİĩ
    0.05
    æѧ
    0.05
    spot
    0.05
    ahn
    0.05
    Activations Density 0.001%

    No Known Activations