© 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. 17104
    Prev
    Next
    INDEX
    Explanations

    since, till, than, to

    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
    çIJĽ
    -0.08
    yant
    -0.08
    pond
    -0.07
    客
    -0.07
    onia
    -0.06
    aur
    -0.06
    姬
    -0.06
    æĺ¯èĥ½
    -0.06
    é£İèĥ½
    -0.06
     Amid
    -0.06
    POSITIVE LOGITS
    ä½Ļ
    0.08
    .extra
    0.08
    è¶ħåĩº
    0.08
    Unnamed
    0.08
    eyond
    0.08
    llib
    0.08
     resto
    0.08
    reiz
    0.08
    åħ¶ä½Ļ
    0.08
    actual
    0.07
    Activations Density 0.051%

    No Known Activations