© 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. 47540
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence algorithms

    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
    elts
    -0.09
    ummer
    -0.08
    extras
    -0.08
    .dtd
    -0.08
    伸å±ķ
    -0.07
    liness
    -0.07
    pee
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
     seksi
    -0.07
    éĿŀ常æĸ¹ä¾¿
    -0.07
    POSITIVE LOGITS
     outputs
    0.09
     algorithms
    0.09
     Outputs
    0.09
    ç®Ĺæ³ķ
    0.09
     algorithm
    0.08
     machine
    0.08
     human
    0.08
    åģıè§ģ
    0.08
     Human
    0.08
     Turing
    0.08
    Activations Density 0.042%

    No Known Activations