© 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. 47959
    Prev
    Next
    INDEX
    Explanations

    signal is, announcement is

    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
    .hasOwnProperty
    -0.09
    çŃīä¸Ģæī¹
    -0.08
    วัล
    -0.08
    çļĦ人äºĨ
    -0.07
    лив
    -0.07
    @d
    -0.07
    æ¥ļæ¥ļ
    -0.07
    ãĤªãĥķãĤ£
    -0.07
    lest
    -0.07
    人åķĬ
    -0.07
    POSITIVE LOGITS
    اء
    0.07
    ayne
    0.07
    alet
    0.06
    alam
    0.06
    aged
    0.06
    ania
    0.06
    ardy
    0.06
    arel
    0.06
    alj
    0.06
    lage
    0.06
    Activations Density 1.521%

    No Known Activations