© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    power and rights

    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
    衬衣
    -0.08
     rall
    -0.08
    éľ²éĿ¢
    -0.08
    оÑĤÑĢе
    -0.08
    ilha
    -0.08
    .googleapis
    -0.07
    enko
    -0.07
    ä¸įéķ¿
    -0.07
    符åIJĪè¦ģæ±Ĥ
    -0.07
    ¹Ħ
    -0.07
    POSITIVE LOGITS
     rights
    0.11
     exerc
    0.11
    æĿĥåĪ©
    0.11
     granted
    0.11
     conferred
    0.10
    享æľīçļĦ
    0.10
    çļĦæĿĥåĪ©
    0.10
     ability
    0.10
     unlimited
    0.10
     prer
    0.10
    Activations Density 0.079%

    No Known Activations