© 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. 19074
    Prev
    Next
    INDEX
    Explanations

    angles and orientation

    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
    edList
    -0.09
    ekor
    -0.07
    æĹłå½±
    -0.07
    eda
    -0.07
    ocene
    -0.07
    atina
    -0.07
    teks
    -0.07
    京
    -0.07
    ooks
    -0.07
    æĹłåıį
    -0.07
    POSITIVE LOGITS
    Latitude
    0.09
     latitude
    0.08
    åįĹæŀģ
    0.08
    ç»ı纬
    0.08
    depth
    0.08
    веÑĢÑħ
    0.07
    imuth
    0.07
    OUTH
    0.07
    (depth
    0.07
    深度çļĦ
    0.07
    Activations Density 0.008%

    No Known Activations