© 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. 27344
    Prev
    Next
    INDEX
    Explanations

    `self.session` or `self.state`

    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
    æĶĴ
    -0.06
    ieres
    -0.06
     Art
    -0.06
     [
    -0.06
    ä¹ĭ
    -0.06
    åŀĭ
    -0.06
    ↵
    -0.06
    holders
    -0.06
    ropolitan
    -0.06
    enes
    -0.05
    POSITIVE LOGITS
    æĶ¶èĹıæľ¬ç«Ļ
    0.08
    acho
    0.08
    åħ¥éĢī
    0.08
    ajos
    0.08
     Gros
    0.08
    å¾·åįİ
    0.08
    illow
    0.08
    é¦ĻçļĦ
    0.08
    æ¯Ķäºļ
    0.08
    icious
    0.08
    Activations Density 0.080%

    No Known Activations