© 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. 49308
    Prev
    Next
    INDEX
    Explanations

    parameters and arguments for code

    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
    ĺIJ
    -0.08
    ardini
    -0.08
    à¨Ī
    -0.08
    ehme
    -0.08
    atical
    -0.07
    erdo
    -0.07
    ī¬
    -0.07
    ssel
    -0.07
    onne
    -0.07
    ième
    -0.07
    POSITIVE LOGITS
    ponge
    0.07
    hape
    0.07
    åºĵ
    0.06
    容
    0.06
    è¿ĶåĽŀ
    0.06
     Warn
    0.06
     âĢļ
    0.06
    gress
    0.06
    çļĦæĺ¯
    0.06
    GRES
    0.06
    Activations Density 0.002%

    No Known Activations