© 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. 56023
    Prev
    Next
    INDEX
    Explanations

    calculating results or outcomes

    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
    allah
    -0.07
     switch
    -0.07
    onta
    -0.06
    implemented
    -0.06
    au
    -0.06
    lichkeit
    -0.06
     entr
    -0.06
    asher
    -0.06
     nonetheless
    -0.06
    ke
    -0.06
    POSITIVE LOGITS
    ioned
    0.07
    Commerce
    0.07
    subpackage
    0.07
    idth
    0.07
    othe
    0.07
    lagt
    0.07
    urement
    0.07
    tay
    0.07
    ´Ī
    0.07
    tiv
    0.07
    Activations Density 0.006%

    No Known Activations