© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14123
    Prev
    Next
    INDEX
    Explanations

    cut off mid‑sentence

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

    No Comments

    Negative Logits
    デザイン
    -18.25
    -pages
    -17.00
     Designs
    -16.88
     aplik
    -16.63
    /design
    -16.50
     pages
    -16.38
     designs
    -16.25
     artworks
    -16.13
     design
    -16.00
    Pages
    -16.00
    POSITIVE LOGITS
     sentence
    37.00
     sentences
    36.50
    句子
    34.00
    sentence
    33.75
     Sentence
    33.50
    句
    31.63
    Sentence
    31.63
    entence
    31.38
    _sentence
    30.38
    _sentences
    27.88
    Activations Density 0.289%

    No Known Activations