© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 14286
    Prev
    Next
    INDEX
    Explanations

    [引] => [起]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     form
    -44.25
     FORM
    -42.50
     Form
    -42.25
    -form
    -41.25
    形式
    -41.00
    _FORM
    -40.50
     forms
    -40.50
    Form
    -40.25
    	form
    -40.25
    .form
    -40.00
    POSITIVE LOGITS
     scores
    17.38
     deposit
    16.13
     score
    15.69
    创造出
    15.25
    _score
    15.00
    文件
    14.94
    Scores
    14.69
    进展
    14.69
     files
    14.63
    Score
    14.56
    Activations Density 1.051%

    No Known Activations

    This feature has no known activations.