© 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. 31049
    Prev
    Next
    INDEX
    Explanations

    polynomials with digits and symbols

    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
    ermen
    -0.07
    ä¸Ģ票
    -0.07
     ev
    -0.07
    erman
    -0.07
    åħ¨åĭ¤
    -0.07
    ökk
    -0.07
    UPER
    -0.06
     Lions
    -0.06
    ষà§įà¦Ł
    -0.06
    _RESERVED
    -0.06
    POSITIVE LOGITS
    .nlm
    0.08
    ivel
    0.07
     nurs
    0.07
    isel
    0.07
    SCO
    0.07
    odb
    0.07
    adj
    0.07
    æĮļ
    0.07
    roe
    0.07
    å°Ķ夫
    0.06
    Activations Density 0.008%

    No Known Activations