© 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. 22310
    Prev
    Next
    INDEX
    Explanations

    alternatives

    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
    Lite
    -0.08
    gangen
    -0.07
    çħŀ
    -0.07
    veni
    -0.07
    unden
    -0.07
    /input
    -0.07
     Lite
    -0.06
    _input
    -0.06
    :description
    -0.06
    bant
    -0.06
    POSITIVE LOGITS
    è¿Ļæīį
    0.08
    egade
    0.07
    estyle
    0.07
    XE
    0.07
    irl
    0.07
    strike
    0.07
     Nevertheless
    0.07
     ebay
    0.07
     decom
    0.06
    prev
    0.06
    Activations Density 0.036%

    No Known Activations