© 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. 65202
    Prev
    Next
    INDEX
    Explanations

    artifacts, errors, noise, contaminants

    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
    NotFoundException
    -0.08
    pla
    -0.08
    igest
    -0.08
    ayload
    -0.08
    andest
    -0.08
    cia
    -0.08
    åıĬéħįå¥Ĺ
    -0.08
    staking
    -0.07
    ำ
    -0.07
    าà¸Ļุ
    -0.07
    POSITIVE LOGITS
     artifacts
    0.09
     artifact
    0.09
     arte
    0.07
    arra
    0.07
    artifact
    0.07
    uppy
    0.07
    夸大
    0.07
     artif
    0.07
    æ£ļ
    0.07
    伪
    0.07
    Activations Density 0.033%

    No Known Activations