© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    say sol

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

    No Comments

    Negative Logits
     perm
    -18.88
     registers
    -18.50
     Registers
    -18.25
    digit
    -18.00
    perm
    -18.00
    (reg
    -17.88
     registry
    -17.88
    Digit
    -17.75
     Emm
    -17.63
    _REGS
    -17.63
    POSITIVE LOGITS
     sol
    67.50
    sol
    57.50
    溶
    55.25
    Sol
    55.00
     Sol
    53.00
    (sol
    51.75
    _sol
    46.50
    .sol
    45.50
     solvent
    33.50
     SOL
    31.13
    Activations Density 0.091%

    No Known Activations