© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51906
    Prev
    Next
    INDEX
    Explanations

    latitude, longitude, altitude

    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
    acial
    -0.07
    zem
    -0.07
    itó
    -0.07
    åIJij被åijĬ
    -0.07
    Female
    -0.07
    edido
    -0.06
    å§Ķæīĺ代çIJĨ人
    -0.06
    说åIJ§
    -0.06
    .sock
    -0.06
    -before
    -0.06
    POSITIVE LOGITS
    ,and
    0.09
    ãģ¨ãĤĤãģ«
    0.09
    åħ±ãģ«
    0.07
    KA
    0.07
    emp
    0.07
    OG
    0.07
    atr
    0.07
    æ··
    0.06
    满
    0.06
    inters
    0.06
    Activations Density 0.400%

    No Known Activations