© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2990
    Prev
    Next
    INDEX
    Explanations

    consciousness state

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

    No Comments

    Negative Logits
    乙方
    -21.75
    簟
    -20.75
     digit
    -19.38
    €
    -17.50
    €�
    -17.38
     цифр
    -17.38
     episode
    -17.25
    Episode
    -17.13
    ’
    -17.00
    (btn
    -16.75
    POSITIVE LOGITS
    ibilit
    12.19
    fait
    11.63
    详
    10.50
     parte
    10.44
    abilit
    10.38
    imum
    10.31
    <Type
    10.25
    odos
    10.25
    赶
    10.19
    詳
    10.06
    Activations Density 4.871%

    No Known Activations