© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2845
    Prev
    Next
    INDEX
    Explanations

    say Ster

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

    No Comments

    Negative Logits
    acket
    -16.50
    掘
    -16.25
    vecs
    -15.75
    -Jun
    -15.56
    	Vec
    -15.50
    煳
    -15.06
    Vec
    -14.81
    润
    -14.63
    út
    -14.44
    -14.38
    POSITIVE LOGITS
     Ster
    51.25
    Ster
    48.25
     ster
    43.50
     STR
    41.75
     Str
    40.50
    ster
    38.25
    STR
    38.25
    Str
    38.25
    str
    37.75
    -str
    37.50
    Activations Density 0.088%

    No Known Activations