© 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. 43021
    Prev
    Next
    INDEX
    Explanations

    unsigned long variables

    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
    иÑĤелÑı
    -0.08
    лÑıÑĤоÑĢа
    -0.08
    -bars
    -0.08
    .absolute
    -0.08
    atically
    -0.08
    ä¹ĭ交
    -0.07
    ences
    -0.07
    壮æĹıèĩªæ²»åĮº
    -0.07
    ERY
    -0.07
    IAL
    -0.07
    POSITIVE LOGITS
    ³
    0.07
    виÑĨа
    0.07
    3
    0.07
    �
    0.07
    2
    0.07
    i
    0.06
    æĤ¦
    0.06
    ampton
    0.06
    ��
    0.06
    Äĥng
    0.06
    Activations Density 0.050%

    No Known Activations