© 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. 24056
    Prev
    Next
    INDEX
    Explanations

    altazimuth, alt-alt, scope, latitude

    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
    讨
    -0.08
    æ¶Ĥ
    -0.07
    æ±Łè·¯
    -0.07
    端åĪ°
    -0.07
     Subway
    -0.07
    uyên
    -0.07
    zsche
    -0.07
    tro
    -0.07
    åİŁæľīçļĦ
    -0.07
    éĢīæĿIJ
    -0.07
    POSITIVE LOGITS
     decl
    0.10
    åįĩèµ·
    0.08
    举åĿ¡
    0.08
    æºĸ
    0.08
     solar
    0.08
    缴å°Ħ
    0.08
     latitude
    0.07
    Decl
    0.07
     Datum
    0.07
    ä¸İå½ĵåľ°
    0.07
    Activations Density 0.003%

    No Known Activations