© 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. 46256
    Prev
    Next
    INDEX
    Explanations

    NMR, protons, nuclei, MR, metabolic

    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
    æī¿æİ¥
    -0.07
    .appendChild
    -0.06
    cratch
    -0.06
    orio
    -0.06
     beyond
    -0.06
    ä»»åĩŃ
    -0.06
    æ²»çIJĨ
    -0.06
    è¡¡éĩı
    -0.06
    åħ´èµ·
    -0.06
    åIJĦç§ij
    -0.06
    POSITIVE LOGITS
    ãĥ¬ãĥ³ãĤ¸
    0.08
    boli
    0.08
    eric
    0.07
    masked
    0.07
    IDDEN
    0.07
    åıijåĩºçļĦ
    0.07
    èıģèĭ±
    0.07
    æīĵæĪIJ
    0.07
    VERAGE
    0.07
    åѤ
    0.07
    Activations Density 0.005%

    No Known Activations