© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2989
    Prev
    Next
    INDEX
    Explanations

    El Niño, symlinks, diagnosis, blood type, universal

    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
    reh
    -0.08
    áĢĦáĢºáĢ¸
    -0.08
    ä¸įçIJĨæĥ³
    -0.07
    çĭĪ
    -0.07
    kert
    -0.07
    뾸
    -0.07
    pek
    -0.07
    dia
    -0.07
    mittag
    -0.07
    quine
    -0.07
    POSITIVE LOGITS
    -like
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    imuth
    0.06
    oder
    0.06
     ((!
    0.06
    à¸ļรร
    0.06
     or
    0.06
    çŃīçī¹æ®Ĭ
    0.06
    åħ¬åı¸çŃī
    0.06
    æĪĸæľª
    0.06
    Activations Density 0.140%

    No Known Activations