© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7419
    Prev
    Next
    INDEX
    Explanations

    "how to"

    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
    mpp
    -0.07
    reu
    -0.07
     lagi
    -0.07
     inf
    -0.06
    该éĻ¢
    -0.06
    èĢ»
    -0.06
    å§Ķæīĺ
    -0.06
    çīº
    -0.06
    æ©
    -0.06
    unde
    -0.06
    POSITIVE LOGITS
    маÑĤа
    0.08
    ạch
    0.07
    idan
    0.07
     Sanity
    0.07
    emony
    0.06
    æŃ£åĪĻ
    0.06
    liy
    0.06
    æĺ±
    0.06
    çĿĢä¸Ģé¢Ĺ
    0.06
    Å¡o
    0.06
    Activations Density 0.089%

    No Known Activations