© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1299
    Prev
    Next
    INDEX
    Explanations

    业务

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

    No Comments

    Negative Logits
    业务
    -17.13
     race
    -16.38
     plot
    -16.13
    Fcn
    -15.81
     UC
    -15.69
     Tib
    -15.44
    	byte
    -15.38
    卡
    -15.25
    患者的
    -15.13
    urv
    -15.00
    POSITIVE LOGITS
    -google
    18.38
     electric
    16.25
    Fish
    15.81
    枪
    15.44
     Immutable
    14.94
    alie
    14.94
    Electric
    14.75
    狼
    14.38
     Sinai
    14.31
    Amazon
    14.19
    Activations Density 0.037%

    No Known Activations