© 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. 61162
    Prev
    Next
    INDEX
    Explanations

    include/xlink

    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
    ÙģÙĦ
    -0.08
    aland
    -0.08
    ogramm
    -0.08
    вакÑĥ
    -0.08
    afil
    -0.07
    écur
    -0.07
    icens
    -0.07
    ossa
    -0.07
    igel
    -0.07
    Ñģмо
    -0.07
    POSITIVE LOGITS
     neutral
    0.07
     pity
    0.07
    parity
    0.07
    _NT
    0.07
    creat
    0.06
     neutrality
    0.06
     parity
    0.06
    ä¸īéŨ
    0.06
     Neutral
    0.06
    EAN
    0.06
    Activations Density 0.001%

    No Known Activations