© 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. 23847
    Prev
    Next
    INDEX
    Explanations

    answer is

    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
    æĥħæľī
    -0.07
    ining
    -0.07
    ormap
    -0.07
    æŃ»çļĦ
    -0.07
    ä½ķåħ¶
    -0.07
    è¿ĺæľī个
    -0.06
    æł¼å°Ķ
    -0.06
    ãģ¨ãģĨ
    -0.06
    č
    -0.06
    æݥ触è¿ĩ
    -0.06
    POSITIVE LOGITS
    upi
    0.07
    éĥ¨åĪĨåĨħ容
    0.07
    uri
    0.07
    dbus
    0.07
    cco
    0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.07
    Outlined
    0.07
    çļĦ主è¦ģåĨħ容
    0.07
    æľī以ä¸ĭ
    0.06
    ippet
    0.06
    Activations Density 0.002%

    No Known Activations