© 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. 18046
    Prev
    Next
    INDEX
    Explanations

    in my or in the

    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
     Ung
    -0.07
    yre
    -0.07
    çĪ±æĪij
    -0.06
    ecret
    -0.06
    orges
    -0.06
     Jal
    -0.06
    .csrf
    -0.06
    容è²Į
    -0.06
    arms
    -0.06
    ä¸Ģæĸ°
    -0.06
    POSITIVE LOGITS
     earlier
    0.10
     previous
    0.09
    ä¹ĭåīį
    0.08
     precedenza
    0.08
     Earlier
    0.08
    ä¹ĭåīįçļĦ
    0.08
     пÑĢедÑĭ
    0.08
    æľīçĸijéĹ®
    0.07
    å¹»
    0.07
    anza
    0.07
    Activations Density 0.039%

    No Known Activations