© 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. 63741
    Prev
    Next
    INDEX
    Explanations

    axis or rotation

    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
    minated
    -0.07
    æĢ»æ¯Ķ
    -0.07
    ê°ij
    -0.07
    æĭīä¸Ŀ
    -0.07
    UPS
    -0.07
    sic
    -0.07
    æĬķéĢĴ
    -0.07
    èªĮ
    -0.07
     Ca
    -0.07
    abal
    -0.07
    POSITIVE LOGITS
     axis
    0.08
     pivot
    0.07
     вÑĢаÑīениÑı
    0.07
    -axis
    0.07
    æŀ¢
    0.07
    æĶ¯çĤ¹
    0.06
     hinge
    0.06
     axes
    0.06
    èĢģä¸ī
    0.06
     rotates
    0.06
    Activations Density 0.006%

    No Known Activations