© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    [identifier] => [identifier]

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

    No Comments

    Negative Logits
     dist
    -16.88
     moral
    -16.13
     cur
    -15.63
     configs
    -15.50
    万象
    -15.06
     pot
    -15.00
     polar
    -14.50
    Mirror
    -14.44
    elsen
    -14.31
     morals
    -14.31
    POSITIVE LOGITS
    identifier
    30.50
     identifier
    28.75
    Identifier
    28.25
    (identifier
    26.50
    _identifier
    26.50
    .identifier
    26.50
     Identifier
    26.13
     identifiers
    22.38
    .Identifier
    21.75
     Gerard
    21.50
    Activations Density 0.022%

    No Known Activations