© 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. 16454
    Prev
    Next
    INDEX
    Explanations

    Python code documentation

    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
    yre
    -0.07
    pery
    -0.07
    loy
    -0.07
    yard
    -0.07
    manship
    -0.06
    oplan
    -0.06
    politik
    -0.06
     Especi
    -0.06
    lias
    -0.06
    tas
    -0.06
    POSITIVE LOGITS
    ï¿£
    0.07
    FileSync
    0.07
    æī¬æī¬
    0.07
    ثر
    0.07
    iming
    0.07
    inster
    0.07
    Ùĩ
    0.07
    èħ¹é»ij
    0.07
    çĶŁäº§çĶŁæ´»
    0.06
    oriously
    0.06
    Activations Density 0.010%

    No Known Activations