© 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. 2587
    Prev
    Next
    INDEX
    Explanations

    say ETA

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

    No Comments

    Negative Logits
     hex
    -27.25
    hex
    -26.88
    Hex
    -25.25
     Hex
    -24.13
     rep
    -24.00
    (hex
    -24.00
    segment
    -23.75
     config
    -22.88
     ret
    -22.88
    段
    -22.38
    POSITIVE LOGITS
     ETA
    17.38
     residues
    16.13
    ETA
    16.13
     residue
    15.44
     �
    15.19
    ув
    14.56
    ivities
    14.25
    ableView
    14.13
     RESP
    13.94
     visited
    13.88
    Activations Density 0.195%

    No Known Activations