© 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. 34273
    Prev
    Next
    INDEX
    Explanations

    machine generated or machine learning

    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
    ridge
    -0.09
    orno
    -0.08
    ness
    -0.08
    minster
    -0.08
    empt
    -0.08
    iente
    -0.08
    erea
    -0.08
    enhagen
    -0.08
    ients
    -0.08
    ances
    -0.08
    POSITIVE LOGITS
    hattan
    0.10
    intosh
    0.09
    ultipart
    0.08
     pencari
    0.08
    ette
    0.08
    atically
    0.08
    andise
    0.08
    brew
    0.07
    erie
    0.07
    /software
    0.07
    Activations Density 0.046%

    No Known Activations