© 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. 1571
    Prev
    Next
    INDEX
    Explanations

    places and living situations

    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
    ensely
    -0.07
    å°Ĩåħ¶
    -0.07
    ents
    -0.07
    orning
    -0.06
    åı¸ä»¤
    -0.06
    ])[
    -0.06
    indu
    -0.06
    ])/
    -0.06
    ÙĦات
    -0.06
    atomy
    -0.06
    POSITIVE LOGITS
     katanya
    0.08
    igli
    0.08
    åIJ¬è¯´è¿ĩ
    0.08
    æľ¬å¸Ĥ
    0.08
     alright
    0.08
    èĢĮä¸Ķæĺ¯
    0.07
    —that
    0.07
    ä¿Ĺ称
    0.07
    æĺłåħ¥çľ¼å¸ĺ
    0.07
     Miser
    0.07
    Activations Density 0.377%

    No Known Activations