© 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. 22897
    Prev
    Next
    INDEX
    Explanations

    budget discussions

    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
    lesh
    -0.07
    heden
    -0.07
    ities
    -0.07
    brew
    -0.07
    qual
    -0.07
     belas
    -0.06
    пÑĭÑĤ
    -0.06
    Ñħождение
    -0.06
    人社
    -0.06
    jol
    -0.06
    POSITIVE LOGITS
    ting
    0.11
    Ø©
    0.11
    ed
    0.09
    ural
    0.09
    eira
    0.09
    -budget
    0.08
    obel
    0.08
    ASIL
    0.08
    taire
    0.08
    ual
    0.08
    Activations Density 0.012%

    No Known Activations