© 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. 46287
    Prev
    Next
    INDEX
    Explanations

    transcription, transducer, transistor, transposable

    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
    -même
    -0.10
     dÃłng
    -0.09
     Äijặn
    -0.09
    ÃŃguez
    -0.08
    à¸ĩาม
    -0.08
    anness
    -0.07
    ock
    -0.07
    yssey
    -0.07
    맺
    -0.07
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.07
    POSITIVE LOGITS
    latable
    0.12
    ylvania
    0.10
    áŁĭ
    0.10
    er
    0.10
    lucent
    0.10
    parency
    0.10
    oare
    0.09
    ponder
    0.09
    ฯ
    0.09
    IGGER
    0.08
    Activations Density 0.092%

    No Known Activations