© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14955
    Prev
    Next
    INDEX
    Explanations

    => 7

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

    No Comments

    Negative Logits
    eel
    -19.63
    alom
    -19.50
    alien
    -18.38
    新加
    -18.00
     clit
    -17.63
    antor
    -17.38
    牒
    -17.00
    salt
    -16.00
    СП
    -15.94
    rema
    -15.88
    POSITIVE LOGITS
    ER
    16.00
    er
    15.38
    رش
    14.81
    池
    14.50
    不如
    13.69
    ut
    13.31
    terr
    13.13
    .erb
    12.94
    nton
    12.81
     minut
    12.75
    Activations Density 0.069%

    No Known Activations