© 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. 49019
    Prev
    Next
    INDEX
    Explanations

    superconductivity and superfluids

    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
    agher
    -0.08
    åįİåķĨ
    -0.08
    _PARSER
    -0.08
    ÙĪØ·
    -0.08
    ãĥ¬ãĤ¹ãĥĪ
    -0.08
    estern
    -0.07
    isia
    -0.07
    ellaneous
    -0.07
    ifix
    -0.07
    lox
    -0.07
    POSITIVE LOGITS
    ç»ĵåĨ°
    0.08
    éĽĨä½ĵ
    0.08
     collective
    0.08
     frozen
    0.08
     Collective
    0.07
    åĨ»ç»ĵ
    0.07
     Ded
    0.07
    è·ĥ
    0.07
     bulk
    0.07
    éĢļéģĵ
    0.07
    Activations Density 0.012%

    No Known Activations