© 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. 10823
    Prev
    Next
    INDEX
    Explanations

    alter, altered, alters

    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
    elled
    -0.08
    rige
    -0.08
    ान
    -0.08
    lify
    -0.08
    ãģĦãģŁãģ®ãģ§
    -0.08
    elling
    -0.07
    keb
    -0.07
    eli
    -0.07
    stitution
    -0.07
    ework
    -0.07
    POSITIVE LOGITS
    ments
    0.09
    ances
    0.09
    äºĨçļĦ
    0.08
    iance
    0.08
    -than
    0.08
    ت
    0.08
    ificial
    0.08
    ather
    0.08
    ÙĨÙĬ
    0.07
    /add
    0.07
    Activations Density 0.015%

    No Known Activations