© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    amended order or opinion

    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
    ovac
    -0.07
    olong
    -0.07
    å¤ļ姿
    -0.07
    inkin
    -0.07
    cape
    -0.07
    éĢ¢
    -0.07
    att
    -0.06
    aters
    -0.06
    =-=-=-=-=-=-=-=-
    -0.06
    ided
    -0.06
    POSITIVE LOGITS
    áĥ
    0.07
    è¿Ļèµ·
    0.07
    é¢ĺ缮çļĦ
    0.07
    åĽ¢åĽ¢
    0.07
    imme
    0.07
    UNA
    0.06
    Ø´Ùħ
    0.06
    umlu
    0.06
    unami
    0.06
    mise
    0.06
    Activations Density 0.004%

    No Known Activations