© 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. 3011
    Prev
    Next
    INDEX
    Explanations

    until, year, throughout

    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
    inherit
    -0.07
    çİīæłij
    -0.07
    ari
    -0.07
    æ²®
    -0.07
    umi
    -0.06
    inq
    -0.06
    çŃł
    -0.06
    occhi
    -0.06
    å¤ĦçIJĨ好
    -0.06
    oggle
    -0.06
    POSITIVE LOGITS
    缴èĩ³
    0.19
    并æľĢç»Ī
    0.16
    缴åĪ°
    0.16
     until
    0.15
    until
    0.15
     вплоÑĤÑĮ
    0.15
     progressively
    0.13
    Until
    0.13
     Until
    0.13
    ä¸Ģ缴åĪ°
    0.13
    Activations Density 0.278%

    No Known Activations