© 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. 48014
    Prev
    Next
    INDEX
    Explanations

    cb context id script

    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
    èĬ®
    -0.07
    ellis
    -0.07
    å½±åĵįåĪ°
    -0.06
    å±Ĥ次æĦŁ
    -0.06
    é§
    -0.06
    lost
    -0.06
     affecting
    -0.06
    å±Ĥ次çļĦ
    -0.06
    å±Ĥ次
    -0.06
    tti
    -0.06
    POSITIVE LOGITS
    æĮĩæŃ£
    0.09
    OBO
    0.08
    anh
    0.07
    isata
    0.07
     dituj
    0.07
    kol
    0.07
    egree
    0.07
    inan
    0.07
    çī¹å°Ķ
    0.07
    uÅŁ
    0.07
    Activations Density 0.001%

    No Known Activations