© 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. 2080
    Prev
    Next
    INDEX
    Explanations

    proposal

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

    No Comments

    Negative Logits
     digit
    -18.63
    digit
    -18.38
     tube
    -17.25
    终端
    -16.13
    Digit
    -15.94
     Tube
    -15.75
    (pat
    -15.69
     digits
    -15.69
     Digit
    -15.50
     tabs
    -15.44
    POSITIVE LOGITS
     proposal
    68.50
     Prop
    66.00
    proposal
    65.50
     Proposal
    62.75
     proposals
    61.75
    Proposal
    61.25
    Prop
    60.50
     prop
    60.50
    prop
    60.00
    _prop
    60.00
    Activations Density 0.204%

    No Known Activations