© 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. 23799
    Prev
    Next
    INDEX
    Explanations

    there exists a

    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
    они
    -0.07
    .docs
    -0.07
    ross
    -0.07
     reflex
    -0.06
    irc
    -0.06
     relevant
    -0.06
     fuck
    -0.06
    شار
    -0.06
    åĪ«è¯´
    -0.06
    ãģªãĤĭ
    -0.06
    POSITIVE LOGITS
     mMap
    0.09
    æĺ¯ä¸Ģåľº
    0.08
    ieno
    0.07
     tight
    0.07
    ANC
    0.07
     aValue
    0.07
    kab
    0.07
     |âĢ¢
    0.07
    ELS
    0.07
     altr
    0.07
    Activations Density 0.002%

    No Known Activations