© 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. 60431
    Prev
    Next
    INDEX
    Explanations

    criterion evaluation

    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
    пÑĭ
    -0.08
    俨
    -0.07
    .localized
    -0.07
    Exposed
    -0.07
    etid
    -0.07
     Mobility
    -0.07
    _YEAR
    -0.07
    enner
    -0.07
    åij¨äºĮ
    -0.07
    _vlog
    -0.07
    POSITIVE LOGITS
    Criteria
    0.10
    riterion
    0.10
     criterion
    0.09
    ç»ĪçĤ¹
    0.09
     visual
    0.09
     Criterion
    0.09
    è§Ĩè§ī
    0.09
    Criterion
    0.09
    æĮĩ示
    0.08
     visually
    0.08
    Activations Density 0.041%

    No Known Activations