© 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. 33490
    Prev
    Next
    INDEX
    Explanations

    expansion

    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
     Destin
    -0.09
     memcmp
    -0.08
    å½ĵãģŁãĤĬ
    -0.07
    izont
    -0.07
    itti
    -0.07
    ÑĤиÑĤ
    -0.07
    æĪ®
    -0.07
    oš
    -0.07
     genomes
    -0.07
    主æķĻ
    -0.07
    POSITIVE LOGITS
     series
    0.10
    .series
    0.09
    ç³»åĪĹçļĦ
    0.09
    ç³»åĪĹ
    0.09
     Series
    0.09
    series
    0.08
     hierarchy
    0.08
    ãĤ·ãĥªãĥ¼ãĤº
    0.08
     série
    0.08
    ä¸Ģç³»åĪĹ
    0.08
    Activations Density 0.005%

    No Known Activations