© 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. 23497
    Prev
    Next
    INDEX
    Explanations

    path and trajectory

    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
     showdown
    -0.08
    大åĪĢ
    -0.07
    åĺĪ
    -0.07
    åIJ«éĩı
    -0.07
    è°ĥåĪ°
    -0.07
    кÑĢов
    -0.07
    egas
    -0.07
     кое
    -0.07
    aylight
    -0.07
    ặn
    -0.07
    POSITIVE LOGITS
    轨迹
    0.17
     trajectory
    0.14
     trajectories
    0.13
    trajectory
    0.12
     traj
    0.12
     trajet
    0.10
     paths
    0.10
     path
    0.10
    è»Į
    0.10
    è·¯å¾Ħ
    0.09
    Activations Density 0.027%

    No Known Activations