© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    both / equal / same

    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
    akis
    -0.08
    éĢī课
    -0.08
    åħ³æ³¨æĪij们
    -0.07
    ÙĪÙĨس
    -0.07
    ãĥĥãĤŃ
    -0.07
    ãĤ¼ãĥ«
    -0.07
    ectos
    -0.07
    Ñĸм
    -0.07
    osphere
    -0.07
    ppi
    -0.07
    POSITIVE LOGITS
     Both
    0.10
     both
    0.09
    Both
    0.09
    both
    0.09
     igual
    0.08
     equally
    0.08
     equal
    0.08
     BOTH
    0.08
    .equal
    0.08
    _both
    0.08
    Activations Density 0.140%

    No Known Activations