© 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. 64884
    Prev
    Next
    INDEX
    Explanations

    track right, left track

    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
    atar
    -0.07
    rena
    -0.06
     Renaissance
    -0.06
    orts
    -0.06
    ilia
    -0.06
    ili
    -0.06
    èı²å°Ķå¾·
    -0.06
    ruk
    -0.06
    ype
    -0.06
    åĪĺæĻĵ
    -0.06
    POSITIVE LOGITS
    åIJĮçIJĨ
    0.09
    åIJĮæł·
    0.08
    ignum
    0.08
     similarly
    0.08
    ä»Ĭ度ãģ¯
    0.08
    亦çĦ¶
    0.08
    alay
    0.08
    .nb
    0.08
     altrettanto
    0.08
    åIJĮæł·çļĦ
    0.08
    Activations Density 0.010%

    No Known Activations