© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8866
    Prev
    Next
    INDEX
    Explanations

    Let or suppose

    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
    دÙĬر
    -0.07
    igham
    -0.07
    ière
    -0.07
    eggio
    -0.07
    çĽ¸ä¿¡ä½ł
    -0.07
    å½¹
    -0.06
    adol
    -0.06
    eed
    -0.06
    åĺģ
    -0.06
    åĨ°å°ģ
    -0.06
    POSITIVE LOGITS
    å©ī
    0.07
    å¸ĥæĸ¯
    0.07
    ChildIndex
    0.07
    amb
    0.07
    blia
    0.06
    ×IJ×ķ
    0.06
    tvr
    0.06
    ths
    0.06
    cca
    0.06
    ancio
    0.06
    Activations Density 0.055%

    No Known Activations