© 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. 18153
    Prev
    Next
    INDEX
    Explanations

    GenBank accession numbers

    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
    çŀĴ
    -0.08
    åģļäºĭæĥħ
    -0.07
    pont
    -0.07
    çķĻç»Ļ
    -0.06
    ãĤĨ
    -0.06
    ož
    -0.06
    è¿Ļ个éĺ¶æ®µ
    -0.06
    åĵ¼
    -0.06
    交åĬŀ
    -0.06
    pah
    -0.06
    POSITIVE LOGITS
    ç¹¼
    0.08
     esclar
    0.08
    ÑĤего
    0.08
    ÑģовеÑģÑĤ
    0.07
    boro
    0.07
    êmes
    0.07
    ÙĨاÙħÙĩ
    0.07
    chg
    0.07
    elves
    0.07
    Encoded
    0.07
    Activations Density 0.054%

    No Known Activations