© 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. 8381
    Prev
    Next
    INDEX
    Explanations

    hydroxy, chemical compounds, acetals

    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
    çĦ¶å¤§
    -0.07
    ERI
    -0.07
    ä»Ĺ
    -0.07
    ç¨İ
    -0.07
    bre
    -0.06
    å±ķå¼Ģåħ¨éĥ¨
    -0.06
    ral
    -0.06
    ห
    -0.06
    åĬ£
    -0.06
    ut
    -0.06
    POSITIVE LOGITS
    lier
    0.09
    abet
    0.08
    ä¸į认è¯Ĩ
    0.07
    ÄįenÃŃ
    0.07
    pered
    0.07
    CBS
    0.07
    pering
    0.07
    etid
    0.07
    YO
    0.07
    unte
    0.07
    Activations Density 0.010%

    No Known Activations