© 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. 15146
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
     Salad
    -19.63
    urger
    -19.25
    olis
    -19.13
    idor
    -18.75
     saline
    -18.50
     salad
    -18.13
    厕所
    -18.00
    atism
    -17.88
    ulum
    -17.75
    ocop
    -17.63
    POSITIVE LOGITS
    微博
    14.38
    STA
    13.31
     pillar
    12.69
    轨
    12.44
     gran
    12.44
     spear
    12.38
    ю
    12.13
     pulse
    12.00
     Spear
    11.94
    Instructions
    11.81
    Activations Density 0.569%

    No Known Activations