© 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. 14967
    Prev
    Next
    INDEX
    Explanations

    plasmon hybridization

    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
     inconsistencies
    -0.06
    å®ļåĬĽ
    -0.06
     Agent
    -0.06
    ISO
    -0.06
    ECH
    -0.06
    rick
    -0.06
    ç»´æĬ¤
    -0.06
     agents
    -0.06
    agma
    -0.06
     ISO
    -0.06
    POSITIVE LOGITS
    _unpack
    0.07
     Bands
    0.07
    plit
    0.07
     комбини
    0.07
    pectrum
    0.07
    bildung
    0.07
     ontstaan
    0.07
    åıijå¸ĥåħ¬åijĬ称
    0.07
    éľĵ
    0.07
     terbentuk
    0.07
    Activations Density 0.008%

    No Known Activations