© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 733
    Prev
    Next
    INDEX
    Explanations

    elephants

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

    No Comments

    Negative Logits
    弋
    -21.13
    谌
    -20.63
     Rossi
    -20.25
     Winnipeg
    -19.25
    长春
    -19.13
     CCS
    -18.00
     Manit
    -17.75
     NC
    -17.63
     CC
    -17.25
     FC
    -17.13
    POSITIVE LOGITS
     elephant
    42.25
     elephants
    41.50
     Elephant
    39.50
    大象
    36.75
    岭南
    33.50
    非洲
    31.00
     Nigerian
    30.63
    珠江
    30.13
     Ivory
    30.00
     African
    29.88
    Activations Density 0.070%

    No Known Activations