© 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. 11282
    Prev
    Next
    INDEX
    Explanations

    iron and its compounds

    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
    hood
    -0.07
    phin
    -0.07
    åĴĮéĩįçĤ¹
    -0.07
    è«ı
    -0.07
    eners
    -0.06
    osing
    -0.06
    RIA
    -0.06
    fristig
    -0.06
    itized
    -0.06
    ombat
    -0.06
    POSITIVE LOGITS
    æĢ§è´«è¡Ģ
    0.11
    ç£ģæĢ§
    0.10
    ife
    0.10
    éĶĪ
    0.09
    èħ¥åij³
    0.09
    iach
    0.08
    zeug
    0.08
    uzzi
    0.08
    ाप
    0.08
    iola
    0.08
    Activations Density 0.026%

    No Known Activations