© 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. 3855
    Prev
    Next
    INDEX
    Explanations

    longitudinal direction

    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
    wehr
    -0.07
    æīĺ
    -0.07
    ault
    -0.07
    grounds
    -0.06
    Ùģاض
    -0.06
     Wid
    -0.06
     broadly
    -0.06
    çļİ
    -0.06
    è¿ĻåŃ©åŃIJ
    -0.06
    ibold
    -0.06
    POSITIVE LOGITS
     longitud
    0.09
    纵åIJij
    0.08
     longitudinal
    0.08
    éķ¿
    0.08
    纵
    0.08
    纵深
    0.08
    itud
    0.07
    rome
    0.07
    è´£ç¼ĸ
    0.07
    åIJijåīį
    0.07
    Activations Density 0.023%

    No Known Activations