© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63043
    Prev
    Next
    INDEX
    Explanations

    true stories and questions

    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
    laus
    -0.10
    à¹Īà¸Ńà¸Ļ
    -0.10
    thon
    -0.09
    obel
    -0.09
    alti
    -0.09
    rush
    -0.09
    ração
    -0.09
    undu
    -0.09
    ahui
    -0.08
    ãģIJãĤĭ
    -0.08
    POSITIVE LOGITS
    /false
    0.15
     Äijắn
    0.09
    heits
    0.09
    à¹ĥà¸Ī
    0.08
    Ùĭ
    0.08
    ,
    0.08
    ulent
    0.08
    haft
    0.07
    -ish
    0.07
    -
    0.07
    Activations Density 0.036%

    No Known Activations