© 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. 2941
    Prev
    Next
    INDEX
    Explanations

    say "caption"

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

    No Comments

    Negative Logits
     reg
    -20.13
    	reg
    -19.50
     pol
    -19.50
    Pol
    -18.50
     Pol
    -18.50
    pol
    -18.38
    利
    -18.25
     Reg
    -18.00
    .reg
    -17.63
     Org
    -17.50
    POSITIVE LOGITS
     caption
    51.00
    Caption
    49.00
    caption
    47.25
     Caption
    47.25
     cap
    46.00
    _CAP
    45.25
    cap
    44.25
     CAP
    44.00
     Capt
    43.50
    CAP
    43.50
    Activations Density 0.036%

    No Known Activations