© 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. 48549
    Prev
    Next
    INDEX
    Explanations

    straightforward way

    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
    aset
    -0.09
    æ®Ĩå°½
    -0.08
    ominated
    -0.08
    ATURE
    -0.08
    ahari
    -0.08
    ursed
    -0.08
    ibera
    -0.08
    thon
    -0.08
    tearDown
    -0.08
    ROTO
    -0.08
    POSITIVE LOGITS
    ly
    0.17
    ness
    0.10
    æĺİäºĨ
    0.08
    LY
    0.08
    æĺĵæĩĤ
    0.08
    ened
    0.08
    ening
    0.08
    à¹Ĩ
    0.08
    ç®ĢåįķçļĦ
    0.07
    èµ·è§ģ
    0.07
    Activations Density 0.009%

    No Known Activations