© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2679
    Prev
    Next
    INDEX
    Explanations

    operator '>'

    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
    obile
    -0.07
    éo
    -0.07
    yra
    -0.07
    çĻ¾å®¶
    -0.06
    icket
    -0.06
    ãĤ¶ãĥ¼
    -0.06
    æĶ¿å§Ķ
    -0.06
    lio
    -0.06
    enc
    -0.06
    .perform
    -0.06
    POSITIVE LOGITS
    å·²ç»ıè¿ŀç»Ń
    0.08
    ãng
    0.08
    αιν
    0.08
    rekt
    0.08
    hti
    0.08
     tadi
    0.08
    åĴĮçĶ°
    0.08
    åĴ¯
    0.07
     previous
    0.07
    æ£ł
    0.07
    Activations Density 0.026%

    No Known Activations