© 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. 2383
    Prev
    Next
    INDEX
    Explanations

    say "params"

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

    No Comments

    Negative Logits
    范
    -24.13
    ,arr
    -20.75
    	util
    -20.25
    modification
    -20.25
    改造
    -20.00
    VAL
    -19.88
    Rev
    -19.88
    Val
    -19.75
     Rev
    -19.63
    arr
    -19.50
    POSITIVE LOGITS
     params
    29.38
    params
    27.75
    (params
    27.63
    =params
    25.25
     Pet
    23.75
     pet
    23.50
    ,params
    22.00
    Pet
    21.50
    	params
    21.25
    _pet
    20.00
    Activations Density 0.080%

    No Known Activations