© 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. 18092
    Prev
    Next
    INDEX
    Explanations

    numbers and letters like -a

    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
     fr
    -0.07
    æIJŀå¾Ĺ
    -0.07
    çľ·æģĭ
    -0.07
    king
    -0.06
     Fr
    -0.06
    egn
    -0.06
    ä¸Ģç«ł
    -0.06
    çľĭä¸į
    -0.06
     aspect
    -0.06
    大åĨĻ
    -0.06
    POSITIVE LOGITS
    byss
    0.08
    Ïģεία
    0.08
    ðŁĺĢ
    0.08
    anches
    0.08
    ç¼ĸåı·
    0.07
    onesa
    0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.07
     Jés
    0.07
    çĶ·åĦ¿
    0.07
    íĺ¸ìĻĢ
    0.07
    Activations Density 0.074%

    No Known Activations