© 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. 27683
    Prev
    Next
    INDEX
    Explanations

    comprehensive assessment and guidelines

    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
    ERY
    -0.09
    çķĶ
    -0.08
    ourn
    -0.08
    شاء
    -0.08
    ORK
    -0.08
    patrick
    -0.08
    ħ§
    -0.08
    URED
    -0.07
    åĮªæµħ
    -0.07
    eph
    -0.07
    POSITIVE LOGITS
    ities
    0.09
    owing
    0.09
    idade
    0.08
    åħ¥å¾®
    0.08
    ि
    0.08
    æĢ§çļĦ
    0.08
    idades
    0.08
    æĪĸå¤ļ
    0.08
    owed
    0.07
    ãģĭãģ¤
    0.07
    Activations Density 0.005%

    No Known Activations