© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16090
    Prev
    Next
    INDEX
    Explanations

    [physical] => [mental]

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

    No Comments

    Negative Logits
    glas
    -16.13
    生命
    -15.50
    鼻子
    -15.44
    腰
    -15.19
     Roses
    -14.94
    生命的
    -14.81
    phon
    -14.75
     bin
    -14.63
    笛
    -14.56
     Gim
    -14.50
    POSITIVE LOGITS
     skl
    17.25
    rch
    15.50
    mdl
    15.38
    spr
    15.00
    spb
    14.56
     attrib
    14.44
    .mdl
    14.44
    /auto
    14.25
    dal
    14.25
     spa
    14.25
    Activations Density 0.070%

    No Known Activations