© 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. 3277
    Prev
    Next
    INDEX
    Explanations

    isotopic evidence

    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
    ä¼¼éĶ¦
    -0.09
    issage
    -0.09
    heds
    -0.09
    edly
    -0.07
    عزÙĬز
    -0.07
    istrator
    -0.07
    ese
    -0.07
    ê°Ŀ
    -0.07
    .cloudflare
    -0.07
    imiento
    -0.07
    POSITIVE LOGITS
    annis
    0.09
    ylum
    0.08
    opes
    0.08
    áĥ£áĥłáĥĺ
    0.08
    ically
    0.08
    verture
    0.08
    足èģĶ
    0.08
     bersangkutan
    0.08
    Ñħоде
    0.07
     Hinblick
    0.07
    Activations Density 0.028%

    No Known Activations