© 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. 29755
    Prev
    Next
    INDEX
    Explanations

    spatial direction 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
    etÅij
    -0.08
    ä¸Ģæ´¾
    -0.08
    åĪ©çī©
    -0.08
    Ñīенко
    -0.08
    éĢļçŁ¥æĪij
    -0.08
    prob
    -0.07
    åŃĺ
    -0.07
     Bakal
    -0.07
    åįĥåįĥ
    -0.07
     Secur
    -0.07
    POSITIVE LOGITS
     dimension
    0.08
    åŀĤ缴
    0.08
    è¾¾åħĭ
    0.08
     vertical
    0.07
    vertical
    0.07
    -wise
    0.07
    ä¸įé½IJ
    0.07
     lẫn
    0.07
    维度
    0.07
     width
    0.07
    Activations Density 0.050%

    No Known Activations