© 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. 15284
    Prev
    Next
    INDEX
    Explanations

    say HTML tags

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

    No Comments

    Negative Logits
    嬴
    -17.38
    OfYear
    -17.00
     Osw
    -16.63
    ZY
    -16.63
    招
    -16.50
     Trees
    -16.13
    洎
    -15.94
    CADE
    -15.94
    ática
    -15.88
    cth
    -15.81
    POSITIVE LOGITS
    弱
    15.50
     labels
    14.31
     unl
    13.75
     sprayed
    13.50
     stronger
    13.19
     label
    13.13
    -strong
    13.13
     strong
    13.00
    命中
    12.63
     gloss
    12.44
    Activations Density 0.062%

    No Known Activations