© 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. 20334
    Prev
    Next
    INDEX
    Explanations

    opposites or extremes

    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
    ãĢıãĢİ
    -0.08
    upd
    -0.08
    ivers
    -0.08
     наÑĢи
    -0.07
    avanja
    -0.07
    ç½ĹéĤ£
    -0.07
    éĤ£éĩĮçļĦ
    -0.07
    ãģĬãģĦ
    -0.07
    VN
    -0.07
    erven
    -0.07
    POSITIVE LOGITS
    两èĢħ
    0.08
    äºĮèĢħ
    0.07
    ãģĿãĤĮãģŀãĤĮ
    0.06
    åIJĦæľī
    0.06
    åĪĨå¼Ģ
    0.06
    åħ©èĢħ
    0.06
    åīįèĢħ
    0.06
    Ø«ÙĨ
    0.06
    ä¸įä½ı
    0.06
    .
    0.05
    Activations Density 0.062%

    No Known Activations