© 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. 48438
    Prev
    Next
    INDEX
    Explanations

    prediction approach

    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
    ustin
    -0.08
    ÏĥÏĦι
    -0.08
    æīĢæľīåĨħ容
    -0.07
    iji
    -0.07
    ikum
    -0.07
     Kha
    -0.07
    Comparer
    -0.07
    agni
    -0.06
    è§Ģå¯Ł
    -0.06
    FieldType
    -0.06
    POSITIVE LOGITS
     based
    0.10
     constructed
    0.09
     calculated
    0.09
    æĺ¯æł¹æį®
    0.09
    åŁºäºİ
    0.09
     predicted
    0.09
    based
    0.09
    æĺ¯åŁºäºİ
    0.09
    为çĶ±
    0.09
    constructed
    0.09
    Activations Density 0.096%

    No Known Activations