© 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. 27474
    Prev
    Next
    INDEX
    Explanations

    partitioning actions or contexts

    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
    cape
    -0.10
    -0.09
    -même
    -0.08
    licherweise
    -0.08
    lix
    -0.08
    udit
    -0.07
    jid
    -0.07
    ildir
    -0.07
    ắt
    -0.07
    ITH
    -0.07
    POSITIVE LOGITS
    ed
    0.10
    icularly
    0.09
    o
    0.09
    alyzed
    0.08
    åĬŀåħ¬åİħ
    0.08
    TEE
    0.08
    ı
    0.08
    oare
    0.08
    ar
    0.07
    ate
    0.07
    Activations Density 0.023%

    No Known Activations