© 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. 16373
    Prev
    Next
    INDEX
    Explanations

    epiphanies

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

    No Comments

    Negative Logits
    LBL
    -18.13
    lla
    -18.00
    Vy
    -17.50
    Ur
    -17.13
    U
    -17.13
    rray
    -16.75
    cean
    -16.75
    igar
    -16.63
    itr
    -16.50
    ivor
    -16.50
    POSITIVE LOGITS
    het
    16.63
     Hein
    16.38
    Ghost
    15.81
    hes
    15.69
    化身
    15.63
    Mess
    15.31
    恐慌
    15.25
    phet
    15.13
     clos
    15.13
     Ghost
    14.88
    Activations Density 0.007%

    No Known Activations