© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42232
    Prev
    Next
    INDEX
    Explanations

    html script tags

    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
    ech
    -0.09
    aiuto
    -0.07
    å½»
    -0.07
    egment
    -0.07
    olini
    -0.07
    acht
    -0.07
    etje
    -0.07
    entials
    -0.07
    alien
    -0.06
    imientos
    -0.06
    POSITIVE LOGITS
    ively
    0.09
    trup
    0.08
    VRT
    0.08
    ivity
    0.08
    vey
    0.07
    sWith
    0.07
    ãģĵãĤį
    0.07
    erait
    0.07
    иÑİ
    0.07
    thead
    0.07
    Activations Density 0.012%

    No Known Activations