© 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. 14359
    Prev
    Next
    INDEX
    Explanations

    [9] => [4]

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

    No Comments

    Negative Logits
    蘑菇
    -18.25
    usz
    -17.00
    菊花
    -16.88
    al
    -16.75
    lz
    -16.63
    ализ
    -16.50
     jelly
    -16.25
     steroids
    -16.13
    �
    -16.13
    inflate
    -15.94
    POSITIVE LOGITS
     sockfd
    19.00
    阚
    17.00
    ocre
    15.44
    俘
    14.44
    ecret
    13.94
     disadv
    13.75
     recap
    13.75
    阊
    13.50
    反腐
    13.50
    /command
    13.50
    Activations Density 0.043%

    No Known Activations