© 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. 32594
    Prev
    Next
    INDEX
    Explanations

    zahlen in texts

    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
    anh
    -0.08
    erson
    -0.07
    agn
    -0.07
    anium
    -0.07
    ely
    -0.07
    ersh
    -0.07
    pector
    -0.07
    iset
    -0.07
    losion
    -0.07
    lessness
    -0.07
    POSITIVE LOGITS
    ãģĨãģ¡ãģ«
    0.07
    ãģĨãģĪ
    0.07
    NotSupportedException
    0.07
    ãĤĵãģłãĤĪ
    0.06
    aphael
    0.06
    ÑĤова
    0.06
    ÑĤи
    0.06
    åĩĮéľĦ
    0.06
    нок
    0.06
    aturas
    0.06
    Activations Density 0.184%

    No Known Activations