© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2696
    Prev
    Next
    INDEX
    Explanations

    say ident

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

    No Comments

    Negative Logits
    .dev
    -18.88
     apparatus
    -16.00
    徐
    -15.94
    registration
    -15.75
     deviation
    -15.63
    ē
    -15.63
    Mor
    -15.31
    uet
    -15.31
     Alo
    -15.25
    装置
    -15.06
    POSITIVE LOGITS
     ident
    42.25
    (ident
    35.00
    ident
    33.25
     Ident
    31.00
    .ident
    29.38
    _ident
    27.63
    _IDENT
    27.25
    Ident
    26.88
     cert
    22.75
     spec
    22.63
    Activations Density 0.011%

    No Known Activations