© 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. 48896
    Prev
    Next
    INDEX
    Explanations

    amount or loss

    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
    _picker
    -0.08
    laš
    -0.08
    xDD
    -0.07
    _LOOKUP
    -0.07
    å¸ĥæŀĹ
    -0.07
    _ASSUME
    -0.07
    èµĦæł¼æĿ¡ä»¶
    -0.07
    cern
    -0.07
    置信
    -0.07
    Lookup
    -0.07
    POSITIVE LOGITS
     total
    0.11
    è´ŁçļĦ
    0.11
    æĢ»é¢Ŀ
    0.10
    åĩĢ
    0.10
    Net
    0.10
    total
    0.10
    æĢ»
    0.10
     totale
    0.10
     losses
    0.10
     Net
    0.09
    Activations Density 0.009%

    No Known Activations