© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14312
    Prev
    Next
    INDEX
    Explanations

    say sessions

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

    No Comments

    Negative Logits
     manufacture
    -18.25
     manufacturing
    -17.13
    urement
    -16.38
    tür
    -16.25
    控制器
    -15.94
    Lim
    -15.81
     pores
    -15.44
    ufact
    -15.31
    dehy
    -15.31
     squid
    -15.19
    POSITIVE LOGITS
     sessions
    25.25
     Sessions
    25.00
    Sessions
    24.38
    -session
    24.38
     Clients
    24.13
    干预
    24.13
     session
    23.75
     Session
    23.63
    Session
    23.25
    sessions
    23.25
    Activations Density 0.812%

    No Known Activations