© 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. 42368
    Prev
    Next
    INDEX
    Explanations

    button is pressed

    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
    zeb
    -0.08
    zyb
    -0.07
    SourceType
    -0.07
    xin
    -0.07
    ynd
    -0.06
    rica
    -0.06
    ẻo
    -0.06
    ALO
    -0.06
    bre
    -0.06
    zyst
    -0.06
    POSITIVE LOGITS
    ayne
    0.08
    ×Ļש
    0.08
    .charCodeAt
    0.07
    arde
    0.07
    ×ķת
    0.07
    ои
    0.07
     راست
    0.07
    害
    0.07
    acct
    0.07
    ÙİاÙħ
    0.07
    Activations Density 0.127%

    No Known Activations