© 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. 25729
    Prev
    Next
    INDEX
    Explanations

    grant or funding source

    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
    ikli
    -0.07
    é«ĺ声
    -0.07
    Docs
    -0.07
    æĬĺ
    -0.07
    sthet
    -0.07
    á»ĥu
    -0.07
    ä¸İå®ŀéĻħ
    -0.07
     Eag
    -0.07
    aco
    -0.07
    igli
    -0.07
    POSITIVE LOGITS
     grant
    0.10
    èµŀåĬ©
    0.09
     grants
    0.09
     sponsoring
    0.09
    grant
    0.08
    èµĦåĬ©
    0.08
     via
    0.08
     granted
    0.08
     Grant
    0.07
    æĶ¯æĮģä¸ĭ
    0.07
    Activations Density 0.062%

    No Known Activations