© 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. 33026
    Prev
    Next
    INDEX
    Explanations

    overlapping areas or multiples

    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
    檻
    -0.08
    åįĥéĩĮ
    -0.07
    ulen
    -0.07
     arrest
    -0.07
     Jud
    -0.07
    åħĥåĴĮ
    -0.07
    edin
    -0.07
     Arrest
    -0.07
    طا
    -0.07
     minori
    -0.07
    POSITIVE LOGITS
    åıłåĬł
    0.09
     overlapping
    0.08
     overd
    0.08
     accumulation
    0.08
     overlaps
    0.08
    åıł
    0.08
    éĩįåıł
    0.07
     overlap
    0.07
    èĥĮæĻ¯
    0.07
     multiples
    0.07
    Activations Density 0.027%

    No Known Activations