© 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. 23793
    Prev
    Next
    INDEX
    Explanations

    circumferential directions

    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
    okus
    -0.08
    åĩºèµĦæ¯Ķä¾ĭ
    -0.07
    ecker
    -0.07
    .ot
    -0.06
    orte
    -0.06
    æĿı
    -0.06
    _hashes
    -0.06
    æijĩæijĩ
    -0.06
    thouse
    -0.06
    otts
    -0.06
    POSITIVE LOGITS
     azimuth
    0.08
    ä¸ĢåľĪ
    0.08
    ¾
    0.07
    èŀº
    0.07
    azen
    0.07
     Ah
    0.07
     roda
    0.07
     circumference
    0.07
     rotational
    0.07
    _rot
    0.07
    Activations Density 0.002%

    No Known Activations