© 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. 40370
    Prev
    Next
    INDEX
    Explanations

    `.sql` or `.sha` suffixes

    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
    è²Į
    -0.07
    æŃ»ä¸į
    -0.06
    apter
    -0.06
    éģį
    -0.06
    æĪij们åħĪ
    -0.06
    ade
    -0.06
    æľĿå¤ķ
    -0.06
    tre
    -0.06
    ìļĶ
    -0.05
    åĢ
    -0.05
    POSITIVE LOGITS
    еÑĩе
    0.08
     Cri
    0.08
     Bem
    0.07
    atina
    0.07
    ullet
    0.07
    ÑĢÑĥд
    0.07
    ä»Ģä¹Īåij¢
    0.07
    ãĥĻãĥ¼
    0.07
    æľĪåĩºçĶŁ
    0.07
    ewing
    0.07
    Activations Density 0.001%

    No Known Activations