© 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. 38058
    Prev
    Next
    INDEX
    Explanations

    un- followed by word roots

    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
    çļĦç¡®
    -0.08
    mando
    -0.08
    igits
    -0.07
    acing
    -0.07
    astica
    -0.07
    -0.07
    ACING
    -0.07
    quires
    -0.07
    ALT
    -0.07
    eschi
    -0.07
    POSITIVE LOGITS
    æĪIJèį¯
    0.08
    æĬĺä¸įæī£
    0.07
     yet
    0.07
     obstante
    0.07
    atak
    0.07
    ori
    0.07
    ness
    0.07
    溶æĢ§
    0.07
    éĹ´æĸŃ
    0.07
    åħī彩
    0.07
    Activations Density 0.260%

    No Known Activations