© 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. 32893
    Prev
    Next
    INDEX
    Explanations

    alkaline

    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
    elage
    -0.08
    romatic
    -0.07
    áĢ¸
    -0.06
    edium
    -0.06
    ailand
    -0.06
    ç¹ģèĬ±
    -0.06
    ail
    -0.06
    teenth
    -0.06
    æĻĮ
    -0.06
    ì¹
    -0.06
    POSITIVE LOGITS
    eous
    0.10
    renz
    0.09
    enment
    0.08
    ymar
    0.08
    ÑĦоÑĢ
    0.07
    -powered
    0.07
    âtre
    0.07
    бин
    0.07
    earch
    0.07
    cito
    0.07
    Activations Density 0.016%

    No Known Activations