© 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. 43543
    Prev
    Next
    INDEX
    Explanations

    chemical formulas, Greek letters, greek letters

    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
    aoke
    -0.07
     infra
    -0.07
    说ä¸į
    -0.06
    使æĪij
    -0.06
    ä¹Łæĺ¯å¦ĤæѤ
    -0.06
    åĬłä¹ĭ
    -0.06
    跳跳
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    stitution
    -0.06
    afc
    -0.06
    POSITIVE LOGITS
     denotes
    0.08
    ugier
    0.08
    urio
    0.07
    .setDefault
    0.07
    enius
    0.07
     denun
    0.07
    iset
    0.07
    éĥ½æĺ¯æ¯Ķè¾ĥ
    0.07
    缮åīįåĽ½åĨħ
    0.07
    æĺ¯æĮĩåľ¨
    0.07
    Activations Density 0.015%

    No Known Activations