© 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. 29224
    Prev
    Next
    INDEX
    Explanations

    hydride generation

    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
    IRA
    -0.09
    ira
    -0.08
    飯
    -0.08
    opoulos
    -0.08
    ungle
    -0.08
    é¥Ń
    -0.08
    ibe
    -0.07
    åĬĽå£«
    -0.07
     inf
    -0.07
    sett
    -0.07
    POSITIVE LOGITS
     numerator
    0.12
    umerator
    0.08
    æĶ
    0.07
    atok
    0.07
     casse
    0.07
    æĢ»éĩı
    0.07
    inium
    0.07
    payload
    0.07
    çĶ³è¯·æĿIJæĸĻ
    0.07
    lán
    0.07
    Activations Density 0.023%

    No Known Activations