© 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. 41673
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    ciano
    -0.10
    erio
    -0.09
    er
    -0.09
    erweise
    -0.09
    aad
    -0.09
    à§įড
    -0.09
    eres
    -0.09
    å¦ĤæѤçļĦ
    -0.08
    aikan
    -0.08
    ÑģÑĮ
    -0.08
    POSITIVE LOGITS
    aneously
    0.09
    æľīç½ijåıĭ
    0.07
    Ø´
    0.07
    «
    0.07
    uctor
    0.07
    ional
    0.06
    ØŃاÙĤ
    0.06
    /out
    0.06
    aneous
    0.06
    qrt
    0.06
    Activations Density 0.027%

    No Known Activations