© 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. 65225
    Prev
    Next
    INDEX
    Explanations

    variation and difference

    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
    nen
    -0.07
    aky
    -0.07
    ÌĢ
    -0.07
    aber
    -0.07
     mic
    -0.06
    åĪ°èĢģ
    -0.06
    aco
    -0.06
    arang
    -0.06
    .getIn
    -0.06
    å°ı鹿
    -0.06
    POSITIVE LOGITS
    缸åºĶ
    0.16
    缸åºĶçļĦ
    0.15
    ä¹Łéļıä¹ĭ
    0.15
    缸æĩī
    0.13
     accordingly
    0.13
     ÑģооÑĤвеÑĤÑģÑĤвенно
    0.13
    éļıä¹ĭ
    0.13
     correspond
    0.12
     pula
    0.12
     corresponding
    0.11
    Activations Density 0.083%

    No Known Activations