© 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. 39426
    Prev
    Next
    INDEX
    Explanations

    0 < x

    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
    iac
    -0.08
    atica
    -0.07
    ÙĥÙī
    -0.07
    çļĦæŃ»
    -0.07
    _bar
    -0.06
    imonial
    -0.06
    ιλ
    -0.06
     Quint
    -0.06
    à¸Ļà¹Į
    -0.06
    ä»»åĬ³ä»»æĢ¨
    -0.06
    POSITIVE LOGITS
    alha
    0.07
    maf
    0.07
    ward
    0.06
    âĢij
    0.06
    ãģĭãĤīãģ®
    0.06
    anÃŃ
    0.06
    å§Ķ
    0.06
    xdf
    0.06
    olina
    0.06
    俨
    0.06
    Activations Density 0.008%

    No Known Activations