© 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. 22920
    Prev
    Next
    INDEX
    Explanations

    station layouts, teams, pancreatic cancer, four homes, his consort, calabrian dialect, journal citation, ostrich hosts, size comparison

    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
    abas
    -0.07
    çĴ§
    -0.07
    ergestellt
    -0.07
    ãģ§ãĤĤ
    -0.06
    .trip
    -0.06
     infos
    -0.06
    redi
    -0.06
    彤
    -0.06
    ãģ§ãĤĤãģĦãģĦ
    -0.06
     Istitu
    -0.06
    POSITIVE LOGITS
    _LVL
    0.08
    èĦ±ç¦»äºĨ
    0.07
    ç¬ĶèĢħ认为
    0.07
    è°Īèµ·
    0.06
    ethyst
    0.06
    ä¹±äºĨ
    0.06
     szemp
    0.06
     urin
    0.06
    åħ¥åº§
    0.06
    åĩłä¸ªæĸ¹éĿ¢
    0.06
    Activations Density 0.023%

    No Known Activations