© 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. 31927
    Prev
    Next
    INDEX
    Explanations

    "now what", "however the", "well through", "here", "this way"

    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
    Ùı
    -0.09
    -0.08
    -0.08
    ़
    -0.07
    Ùİ
    -0.07
    ÙıÙij
    -0.07
    ÌĢ
    -0.07
    ecam
    -0.07
    -0.06
    .utf
    -0.06
    POSITIVE LOGITS
     seperate
    0.08
    &T
    0.06
    oret
    0.06
     again
    0.06
     kedepan
    0.06
    again
    0.06
    onal
    0.06
    *\
    0.06
    ade
    0.06
    ÑĥÑģа
    0.06
    Activations Density 0.899%

    No Known Activations