© 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. 19420
    Prev
    Next
    INDEX
    Explanations

    large, big, huge

    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
    heber
    -0.08
    VERR
    -0.08
    zuh
    -0.08
    /ay
    -0.08
    _ATTRIB
    -0.08
    æij©æ´Ľ
    -0.08
    åĬĽæĮº
    -0.08
    çĻ¾å®¶
    -0.07
    æĪIJç«ł
    -0.07
    udge
    -0.07
    POSITIVE LOGITS
    ä½Ĩåıªè¦ģ
    0.08
     goog
    0.07
    æķ°ä¸ĩ
    0.07
    illions
    0.07
    hn
    0.06
     efficiently
    0.06
    è¿ľè¶ħ
    0.06
    ijIJ
    0.06
    string
    0.06
     comput
    0.06
    Activations Density 0.018%

    No Known Activations