© 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. 42179
    Prev
    Next
    INDEX
    Explanations

    not sure

    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
    ourcem
    -0.10
    æľ¬æ¥¼
    -0.09
    ditor
    -0.09
     تÙĤرÙĬب
    -0.09
    IfNeeded
    -0.09
    ernal
    -0.09
    à©
    -0.09
    erei
    -0.09
    .Qual
    -0.09
    ertest
    -0.09
    POSITIVE LOGITS
     how
    0.08
     whether
    0.08
    how
    0.07
    åħ·ä½ĵçļĦ
    0.07
     whereabouts
    0.07
    æĺ¯åIJ¦éľĢè¦ģ
    0.07
    åħ·é«Ķ
    0.07
    åħ·ä½ĵ
    0.06
    th
    0.06
    ;
    0.06
    Activations Density 0.026%

    No Known Activations