© 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. 51496
    Prev
    Next
    INDEX
    Explanations

    twice as/the

    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
    ksam
    -0.09
    ersten
    -0.09
    ä»ģæħĪ
    -0.08
    ä¸ĵ家æĮĩåĩº
    -0.08
    wein
    -0.08
    ezz
    -0.08
    ointments
    -0.08
    rech
    -0.08
    spflicht
    -0.08
    optimizer
    -0.08
    POSITIVE LOGITS
     the
    0.10
    ly
    0.09
     than
    0.09
    -ish
    0.08
    en
    0.07
    Âł
    0.07
    .nlm
    0.07
     of
    0.07
    åĢįçļĦ
    0.07
    the
    0.07
    Activations Density 0.028%

    No Known Activations