© 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. 3652
    Prev
    Next
    INDEX
    Explanations

    code snippets and related context

    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
    å¾Ĺä½ĵ
    -0.07
    loc
    -0.07
    妥å½ĵ
    -0.06
    uch
    -0.06
     synonym
    -0.06
    os
    -0.06
    nd
    -0.06
    ng
    -0.06
     consecu
    -0.06
    olly
    -0.06
    POSITIVE LOGITS
    itional
    0.09
    icode
    0.09
    icular
    0.08
    åįĩæĹĹ
    0.08
    heed
    0.08
    iono
    0.08
    aren
    0.08
    θÎŃ
    0.08
    æľĪçĶŁ
    0.08
    .Generate
    0.07
    Activations Density 0.006%

    No Known Activations